SimpleNet: A Simple Network for Image Anomaly Detection and Localization |
![GitHub](https://camo.githubusercontent.com/7fa2cf50928ee681ca97ef5e1d6fe6dc029f073100ff901449fd928f52bb26f2/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f446f6e616c6452522f53696d706c654e65743f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/fba4c95192aaa506b715632a5c5214916c5ea84e6b0f1b6c4bc575530e06ac8a/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31353134302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Masked Image Modeling with Local Multi-Scale Reconstruction ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
![GitHub](https://camo.githubusercontent.com/1d78e1decd0082a7ca645fc30b82c03f586e1d1ea11db625bd7c7f5c7472acc5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f48616f71696e672d57616e672f4c6f63616c4d494d3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/5c6036deabafd65f1658c50586c6cb92e24a97013cf7dd09a0c38450e2f795f6/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e30353235312d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders |
![GitHub](https://camo.githubusercontent.com/8bb58796ebafde1f872cc3a0e625acd70d2e09297dad3a60f635b61a87614b12/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f77676362616e2f6164616d61653f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/481e535bee45ebe9d66ee33fbd9b0a12fe8077e9d1ebee4041a77367df8f92ac/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e30393132302d6233316231622e737667) |
➖ |
ActMAD: Activation Matching to Align Distributions for Test-Time-Training |
![GitHub](https://camo.githubusercontent.com/5be411779cdb10608cd5538053cb16cae974103e074b84474926e170546b0c3a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6a6d69656d69727a612f4163744d41443f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/096ed962cfb250cf430423b94f4b0dc06242ea7c938ec30317a4297b415d074f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e31323837302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling is All You Need |
![GitHub](https://camo.githubusercontent.com/ae66f58983a24113f26139eef2d13acfb3bff6f4cab48fb8eed2037c7086c6e9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4a756c6965744c4a592f4d4f4f443f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/250bcc83f76c71b7f3de2d200768d6a3c0a446e456ccf52ee743f872738c37c9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330322e30323631352d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
DLBD: A Self-Supervised Direct-Learned Binary Descriptor |
![GitHub](https://camo.githubusercontent.com/ac9d15d3a81bf03450fee39605b4b5d818bcb222fabcb2e1fc2c30cb0677cf93/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f43515550542d43562f444c42443f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Cut and Learn for Unsupervised Object Detection and Instance Segmentation |
![GitHub](https://camo.githubusercontent.com/afff3fe5ca64d5607e6a30547d902be88f2861b691f0e85a3356eee2a41b2ece/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f66616365626f6f6b72657365617263682f4375744c45523f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/538f5de0d4ec2c7a74cb59f7ec545df59e65336b39c38b0ef78e05611e00b04a/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330312e31313332302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration |
![GitHub](https://camo.githubusercontent.com/121e823f2964e1ce2725f1bc77debaf2cc846038e8677366513120c3f6fca80b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f67666d65692f5544505265673f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/752aaa8fcea90ef6dd4aae3b874af0163fc29ee6c197a3fdfed780ab2060e263/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31333239302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Masked Motion Encoding for Self-Supervised Video Representation Learning |
![GitHub](https://camo.githubusercontent.com/e9a00a04ae0c947d00cc38727786a51849e05fef0bfa91659db7c7d77647b574/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f58696e797553756e2f4d4d453f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/ca81b36e1285d8ae1821867f1c51a95974663238c5089bc62e24d185d7056a0e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231302e30363039362d6233316231622e737667) |
➖ |
Stare at what You See: Masked Image Modeling without Reconstruction |
![GitHub](https://camo.githubusercontent.com/e5cb7d04654885c83b636b71f87e9659740b61ff3598ac1239a72621c64d5ba0/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f70656e44726976654c61622f6d61736b616c69676e3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/fe7d83cc121c55da50620fc00894f7dbd50430119f60d7bef9fb7bd0c6a73725/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e30383838372d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Hard Patches Mining for Masked Image Modeling |
![GitHub](https://camo.githubusercontent.com/21d99ad301303b0f31159d0c5127d5b24e16805269c8d7d665069cb4d62f5a2d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f48616f6368656e2d57616e673430392f48504d3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/471b870695fe52bef6395844a778e1b127c378694086634eb0b8ee671137c73b/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330342e30353931392d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning |
![GitHub](https://camo.githubusercontent.com/840e0dcd3402965d63b9ae3a308bb6f1de426d6a339c9104ff31f747b395e71c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f736b796f75782f6d6f6b643f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/4867f606db94d1251fc9ec1e1ce7aea2bec34218398bf68968ce298e40d9ac45/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330342e30363436312d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
![GitHub](https://camo.githubusercontent.com/d6f3d984830871575083f4b2918e988a2e1d5ddf6072ff459cc5a256f5edafef/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f62616169766973696f6e2f4556413f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/7363135648efd3a4b3c27ea71e39a49bdb1f49c0bfb63d55c6cbc691cf0c2d17/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e30373633362d6233316231622e737667) |
➖ |
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis |
![GitHub](https://camo.githubusercontent.com/4a80ef41544d83a9932fe74b96fce8add76d2f1341a69a0434f0eddd3f9fa669/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4c544831342f6d6167653f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/6ee22820a859c1a01cff6986df552e6330832ad979d11cd744a362c2a7a805c1/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e30393131372d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training |
➖ |
![arXiv](https://camo.githubusercontent.com/7a485ee02bc277a686f5e837cbf00ce8b065c00dc5dfeba7ad84d3a9d9af1bbc/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330342e30343137352d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving |
➖ |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond |
➖ |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
➖ |
Integrally Pre-Trained Transformer Pyramid Networks |
![GitHub](https://camo.githubusercontent.com/f02f7812a9d90cf38b9ec0c15f367a1d77a505c1cd2c5939daf7965f42404a98/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f73756e736d61727465726a69652f6954504e3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/f514ad940d46d147fb97eb70b84260f9acb0c6434d816bee0b81b45b78709550/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e31323733352d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Mixed Autoencoder for Self-Supervised Visual Representation Learning |
➖ |
![arXiv](https://camo.githubusercontent.com/eedf567e095bea25f72abb562ea8a59ac8cc87e9a435d79e2a2da4a47fd7e461/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31373135322d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Correlational Image Modeling for Self-Supervised Visual Pre-Training |
![GitHub](https://camo.githubusercontent.com/665543e2a6761a9487ebbac74777a8b92f7f1bb3ead1aaf7bc48dd6b022b09cf/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f776569766973696f6e2f436f7272656c6174696f6e616c2d496d6167652d4d6f64656c696e673f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/18c95535c25f3c457d366cf9bab6e892da650da7ca81b84a36e6243f1a2ed28e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31323637302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning |
![GitHub](https://camo.githubusercontent.com/34e706734135f7787af21280b240fe2421bacee5e517306f2b848d90b87c0a14/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f626a6563742d756e6465727374616e64696e672f534c4153483f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/af3112d0db87ba5233f162f912c115f7c5bdb829bec37ce8c40e2b4220f6a2e4/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31373834322d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric |
![GitHub](https://camo.githubusercontent.com/34f86b1c0bb521c2bae1d5af6794ea8601ac33b8a1f989c54a4e12190326f984/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f584c6561726e696e672d5343552f323032332d435650522d46434d493f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/f1a7249b442fbeb856f7b8c9110f5ec94420b2abe6ea9a02183d2c368eecade7/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230392e31323339362d6233316231622e737667) |
➖ |
Evolved Part Masking for Self-Supervised Learning |
![GitHub](https://camo.githubusercontent.com/b2317682a67f3d09ff413dd95929947b8a3db5ef4d94681035826e005c01d731/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5a68616e7a686f7546656e672f45766f6c7665642d506172742d4d61736b696e673f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
➖ |
Change-Aware Sampling and Contrastive Learning for Satellite Images |
![GitHub](https://camo.githubusercontent.com/c04a242a1a28f06bb57a153efceca50d9e01a22d0d6b8c4e79b8e038ead6f330/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f75746b617273686d616c6c31332f6361636f3f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems |
![GitHub](https://camo.githubusercontent.com/86a985310b576b2bf4cfacaf17305bba90484f69f0f51a7dfa2071aa87864376/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f47414e506572662f4c43523f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/862b81fea70872c15f926e48951de83eb0d0845a868254885746e8a4a4bb3125/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e30313636392d6233316231622e737667) |
➖ |
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks |
![GitHub](https://camo.githubusercontent.com/173546595f29f674bb822fd388ec50b4bacb2737b68c251fb0f0ae4ad980d0ba/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6a696d6d792d64712f44726f704d41453f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/ad1d1fc126d4e6f9e8e9cf527897876d3ddd2a21956828ced3aef7b09dd808de/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330342e30303537312d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
RILS: Masked Visual Reconstruction in Language Semantic Space |
![GitHub](https://camo.githubusercontent.com/3ddd3a8c285e2d4168a273de2969b9c62b5200d140c617998890806e74dbbcb5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f68757374766c2f52494c533f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/8315c45c4f9101bb6fcfab8c89fc24273d75e47877b23027c2e45c665842b03f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330312e30363935382d6233316231622e737667) |
➖ |
Three Guidelines You Should know for Universally Slimmable Self-Supervised Learning |
![GitHub](https://camo.githubusercontent.com/d3be6c99ccf138293b790f0d6341130581a4b58a8586079ebeae5a0ab6ef3f6b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d65677669692d72657365617263682f5553334c2d43565052323032333f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/7379e277e01e160cb84fc48d8b6300182c5cde7ea95d4bdecef5728a3e3b5433/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e30363837302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
BASiS: Batch Aligned Spectral Embedding Space |
➖ |
![arXiv](https://camo.githubusercontent.com/976fcf27f38469ee8984351bfaa47207c6fae8af6b39aa8000af4985821c5ddf/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e31363936302d6233316231622e737667) |
➖ |
Co-Salient Object Detection with Uncertainty-Aware Group Exchange-Masking |
➖ |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Hyperbolic Contrastive Learning for Visual Representations beyond Objects |
![GitHub](https://camo.githubusercontent.com/2995e820e042c025642fd542d770eaf6e933658c5817e50a29fd31344883a780/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f73686c6f6b6b2f48434c3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/9f0457d01abe02a7fa2f7e5e71f743c3ad45f681d792ae9497c357cf29ec451e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231322e30303635332d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm |
![GitHub](https://camo.githubusercontent.com/35218f233611e074250b94dfb56a945db7ad710db4943583b1024ff7c5e6de85/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f79696368656e3932382f41637469766546543f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/dacb77658b80dd248b4ffe17b9e00e3f1bdd9bd7a934a64d9a179554d427d7ae/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31343338322d6233316231622e737667) |
➖ |
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-based Self-Supervised Pre-Training |
![GitHub](https://camo.githubusercontent.com/b51648e1c1afd0601e5240e3f8a54eaeb59088ca035ae5819d5681d57c296a0a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f70656e526f626f744c61622f4d562d4a41523f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/018c69aa9d882b3ac65af2d9db25dce46c315eaa96d88deafc5c35c566c55903/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31333531302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization |
➖ |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
➖ |
TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models |
![GitHub](https://camo.githubusercontent.com/a29de9f1732c0662e192327872319a61e116fd195f2321f64ed15fc7d0a7e0ad/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f6c6976657252656e73752f54696e794d494d3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/abbb9fa6bb624b937d388d9cc46a74673e554b67ee17eafe76a0b1ab9f11b41f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330312e30313239362d6233316231622e737667) |
➖ |
ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation |
![GitHub](https://camo.githubusercontent.com/6b5ea7bf1257a24236a9b04255aafbd504dd95be8722cb83872cf3e1aa2c6f8d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f76616c656f61692f414c534f3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/7e14ad8f01722df34d41691bd1a5ba35ba6cd9ee638c822703a42fe9fa73a213/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231322e30353836372d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Non-Contrastive Unsupervised Learning of Physiological Signals from Video ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
![GitHub](https://camo.githubusercontent.com/ca21dcd5bf5bb1f3d6783464222f9eb5e33a92102bc9cf91a0c1c1f6d75ac7ed/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4356524c2f53694e432d725050473f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/e349945e5e1924dbc2f9069ddea1f67843507b168a998aac0d1299ded2776c8e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e30373934342d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning |
![GitHub](https://camo.githubusercontent.com/696c325370140938e6638b9c5bcddad40e33452cfc4a89fba0174e836fd73090/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f737465676d75656c2f43724f433f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/147ae76cfb9bd59d06c1595fc20d3c7d0e22a39fcfd11002033c781193072d3f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31333234352d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
MOVES: Manipulated Objects in Video Enable Segmentation |
![GitHub](https://camo.githubusercontent.com/a38af4df951623e648b883532fe2e00840e4e90693f87db5857aa3c304a56af7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f72656c682f6d6f7665733f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Self-Supervised Representation Learning for CAD |
➖ |
![arXiv](https://camo.githubusercontent.com/f70777153358dd6e37d242e68e068a86e18877d983de475096c6f465e53722bd/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231302e31303830372d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Movies2Scenes: using Movie Metadata to Learn Scene Representation |
➖ |
![arXiv](https://camo.githubusercontent.com/06a43f99a0c8d06a09dd1c094f305efc7d130faf2b65f02e30cb9712c9420ca4/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230322e31303635302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos |
![GitHub](https://camo.githubusercontent.com/f8487453573f8b18f1ed82a1d2a427913dfb9d958e7da2982af6811ab9420313/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4a6f686e736f6e5369676e2f506f696e74434d503f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/8239b147097d4a38a29dd6fdab2d20ce9deda4d09f566d1ea867f0be6d8a434a/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330352e30343037352d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Texture-guided Saliency Distilling for Unsupervised Salient Object Detection |
![GitHub](https://camo.githubusercontent.com/c9ae577ce7332c2b373f61d88d9b202015f2c39f323fec7590e546e944ab7af4/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6f6f746865732f4132532d76323f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/11236bb3367a7c32f3160612bfa19a90ec99abcc59c1ef05c13c9dfe042eabb9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230372e30353932312d6233316231622e737667) |
➖ |
Multi-Realism Image Compression with a Conditional Generator |
➖ |
![arXiv](https://camo.githubusercontent.com/b0ed25c7827b8a8759f27eec62a1bfecf67be271394165960f6480955b833730/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231322e31333832342d6233316231622e737667) |
➖ |
Understanding Masked Autoencoders via Hierarchical Latent Variable Models ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
![GitHub](https://camo.githubusercontent.com/54eb986e8333594940b684dc602f1ed6bcc838ed4366bb4c97293f396b80ff70/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d617274696e6d616d716c2f6d61655f756e6465727374616e643f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/47cb4c7a9b625225c91b0d80d357688d8b64f4d8788e38504c322fb3cc54f0b3/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330362e30343839382d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training |
![GitHub](https://camo.githubusercontent.com/71c46e269d208c6a8bc64de0a8ef0fbb32532b1ab11c50e0a241f1f14aefad09/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5473696e676875612d4d4152532d4c61622f47656f4d41453f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/8f369df32fd1a7e4880ff8e0e5b8d8dff74b46c39d3d28b6622814d18281fe93/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330352e30383830382d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Siamese DETR |
![GitHub](https://camo.githubusercontent.com/283b201695fa870798ef7c841acf2ba5cfba79f0a2e60b9df199acf8bec276f3/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5a7835352f5369616d657365444554523f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/9f766cf3079a8cf026a0709680befd11d131bd571d4f9c718e5e0b9fb5d91335/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31383134342d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Generalizable Implicit Neural Representations via Instance Pattern Composers ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
![GitHub](https://camo.githubusercontent.com/ddc80cb5096ca2d53651bb852fe8fc5af398a41416ea92a36017e6af2e30e168/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6b616b616f627261696e2f67696e722d6970633f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/b5eaca8259c1a08160eb157c45fbbf8844a550d1b6d55c3ddfa48a309a2eafc5/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e31333232332d6233316231622e737667) |
➖ |
Pose-Disentangled Contrastive Learning for Self-Supervised Facial Representation |
![GitHub](https://camo.githubusercontent.com/807c93780dcd8f05dd748787192296243cbd569127d4878ac3f17ba807532d89/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f447265616d4d722f50434c3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/2a2fb421f3a16d88d21f73d431d8a72e0a3521b80d1c3ea8692011191118c944/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231312e31333439302d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
OT-Filter: An Optimal Transport Filter for Learning with Noisy Labels |
![GitHub](https://camo.githubusercontent.com/af16449c98c1a4572e3b8b197be89e1d019d44fb0012944e0897b7e1f75ca30c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f72796c303432372f436f64652d666f722d4f542d46696c7465723f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
➖ |
Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models |
![GitHub Page](https://camo.githubusercontent.com/90f3cb3e0cd1967bf7bc2cfd84227aba28b93421cf493bb52d929774f5c053be/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4769744875622d506167652d3135393935372e7376673f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Spatio-Temporal Self-Supervised Learning for Point Clouds in the Wild |
![GitHub](https://camo.githubusercontent.com/0e15433d5674bc2900c623dd7db2c2251fef7949b044763c2dea654544b7cc08/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f59616e68616f57752f535453534c3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/a98f5af83882f36f56e05810cc2efdb85358da2214d506c9209e48bb27ca038e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31363233352d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos |
![GitHub](https://camo.githubusercontent.com/51299c2a3eec0c04aff8ac1ee1e7024c001416c08bf5948f868b00dcfaad0add/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6e6575726f6574686f6c6f67792f424b696e442d33443f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/f4ee80cc2b40b64b6df5c2a990c664d53e3ebaadf1ac605813c860b48ed51668/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231322e30373430312d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Learning Decorrelated Representations Efficiently using Fast Fourier Transform |
![GitHub](https://camo.githubusercontent.com/3f56fca88374b0da75fb0ecb512438e2a519e0d5d1f7d42e610a7a6ccfe8fee5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f79757461726f2d732f7363616c61626c652d6465636f7272656c6174696f6e2d73736c3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/157229644fe0ee36afb4511c403d5ce811afcecaf72b884f60696ba34fe71cab/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330312e30313536392d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks |
![GitHub](https://camo.githubusercontent.com/119c864a39511158fcf5fe2d982212ec83efda7a6fc71757d80875079d0324ec/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f74696e79766973696f6e2f534f4c494445523f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/a446a9f47e2088ff242f9bb54abd0020b8400ba4f1634cf5c9d17ffd7fe11f61/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31373630322d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Learning Geometry-Aware Representations by Sketching |
![GitHub](https://camo.githubusercontent.com/6e40e0b93da9b925757fd770fa62d8198f49d48950cfab32ddc87f266866a226/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f696c6c6879686c313131312f4c6561726e696e674279536b65746368696e673f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/137a7fdc48aced1e548e098d0c98da91b58027fb64333d10763beec67b74976c/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330342e30383230342d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Improving Visual Representation Learning through Perceptual Understanding |
![GitHub](https://camo.githubusercontent.com/cc07726026b9b826995001e7cf4a4ceb5fca50b814b57cd9adbccf71a61cc58a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f747261637461626c6561692f7065726365707475616c2d6d61653f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/4bdf0a1bc6e98c74d08a7a4797321544a4e8aa4058534ccb580009dcaf924330/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231322e31343530342d6233316231622e737667) |
➖ |
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers |
![GitHub](https://camo.githubusercontent.com/feec772ee3077a0cecc66c8ea4995cd08944fc81f54812f860573887a3333dca/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f53656e73652d582f4d69784d494d3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/f015edc7bf793f029dcc4fd54b4e1d33c9d6811a07af252e9e3a33d9aa7b52ef/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230352e31333133372d6233316231622e737667) |
➖ |
Unsupervised Object Localization: Observing the Background to Discover Objects |
![GitHub](https://camo.githubusercontent.com/99bc0a7752c131bead8c3ed6ed2d4b5d3d80d4d503da53295cd38c77a0814d6b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f76616c656f61692f464f554e443f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/cf52f06b18a153f486ae4927494cbcf2906b5d4d8654cd81b3236a6d18cfe124/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323231322e30373833342d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation |
![GitHub](https://camo.githubusercontent.com/04d6afa2c024085f1d4567a300d1ae7578436e6d53ecac40417f5b29f5eb0f36/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5759432d3332312f4d43463f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
DivClust: Controlling Diversity in Deep Clustering |
![GitHub](https://camo.githubusercontent.com/4bc7dee376abd8c23f48406ef8df38650f1cb8879f66ce4de8810f97b53ca5ec/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4d616e6961646973472f446976436c7573743f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/d5c9d3e73222f2a8fff94b9b8d88feb883adb55b23cc0050cc8892e585caf357/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330342e30313034322d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
On Data Scaling in Masked Image Modeling |
➖ |
![arXiv](https://camo.githubusercontent.com/6f8c2785851246b065ee60d2cf30578c5c5474672852171344f387dca5c9fb78/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230362e30343636342d6233316231622e737667) |
➖ |
Revealing the Dark Secrets of Masked Image Modeling |
![GitHub](https://camo.githubusercontent.com/f1a0eeab67c701c1e7fdaf282d3e87d02acfaaa43dac5d905c3977c54770f16b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5377696e5472616e73666f726d65722f4d494d2d44657074682d457374696d6174696f6e3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/61a2f39f286825a39d91a815ffca2488bcdb54f5eb590520c66ab369a0d9cde9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230352e31333534332d6233316231622e737667) |
➖ |
Open-Set Representation Learning through Combinatorial Embedding |
➖ |
![arXiv](https://camo.githubusercontent.com/1b2e430d0ea0e03c79adf58f43c0bc225d296d8d7bea5d79b7f5e9bca7ff6713/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323130362e31353237382d6233316231622e737667) |
➖ |
Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning |
![GitHub](https://camo.githubusercontent.com/f203a566cce6640a6912b968bf03d29be4022a06c079d26ffcd0cccb0bcde236/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f73756e676e79756e2f6f70656e73736c2d73696d636f72653f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/30543b886069426f04be770dc55e50e2d2345d50fb9f681018e0ebdce85e6e65/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31313130312d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling |
![GitHub](https://camo.githubusercontent.com/a2ac8e032fe832f93eb328dbaba3058959f67aa21f59a663bb43cf8baabd906f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4c7963636c2f546f746865706f696e743f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
➖ |
MetaViewer: Towards a Unified Multi-View Representation |
![GitHub](https://camo.githubusercontent.com/f8e2a6ae4e73f688c67077d95fba13b4dc16d5c1da246f9ed8b40c8522fc46c7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f78784c6966654c6f7665722f4d6574615669657765723f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/7d9a1818742f31c5ee217c68d3510d897866e7d3abe3b35f05c3184065c906fb/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e30363332392d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture |
![GitHub](https://camo.githubusercontent.com/ad4129f35e09fa0747abf8096b22bd64550ccf46bf9920c582b932b7b976bca2/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f66616365626f6f6b72657365617263682f696a6570613f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/d09c57ab639e48aa7e26e69090e98e98c75b25281b4bfea13cc25002408160e1/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330312e30383234332d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Understanding Masked Image Modeling via Learning Occlusion Invariant Feature ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
➖ |
![arXiv](https://camo.githubusercontent.com/a4e709851fac4cf68f683977cea8545ca4331b14a48f0734908cfc03b31983d6/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323230382e30343136342d6233316231622e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning |
![GitHub](https://camo.githubusercontent.com/14187cfd243444921ecd6445035c1bd56bae344a4a4a3ddbb363425237978102/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7361696c6973742f43484d617463683f7374796c653d666c6174) |
![thecvf](https://camo.githubusercontent.com/570147fbf0c4aade041dc1e76b9cc9cc802ebdef0c7e20c98df264ef7919b215/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f7064662d7468656376662d3733393543352e737667) |
![YouTube](https://camo.githubusercontent.com/4c91b5d587f82e3ea0df6978845aea9370200c5f626a2fa7d6e48d2db40c8aa0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f596f75547562652d2532334646303030302e7376673f7374796c653d666f722d7468652d6261646765266c6f676f3d596f7554756265266c6f676f436f6c6f723d7768697465) |
Regularize Implicit Neural Representation by Itself ![CVPR - Highlight](https://camo.githubusercontent.com/5cb496e2b9e24dbb9469b9fdf6f120a9d249de14965ea65e1c41199f309ceac9/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f435650522d486967686c696768742d464646463030) |
![GitHub](https://camo.githubusercontent.com/b8b6bd49cb590653fd5335a7e860f367be81632137fdeaf0d25e7566c328fae5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f59616e6e69636b53747275656d706c65722f696e725f62617365645f636f6d7072657373696f6e3f7374796c653d666c6174) |
![arXiv](https://camo.githubusercontent.com/a97aa69e02fa612ef11a587510cca24728d399adeb272ccd5c821f0f091aaa0d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f61725869762d323330332e31353438342d6233316231622e737667) |
➖ |