🔥Highlighting the top ML papers every week.

Codes for "Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation" in CVPR 2021

🍣 국내 스시 오마카세 맛집 리스트

[NeurIPS 2021 Spotlight] Learning to Compose Visual Relations

Anomaly detection is a common problem that is applied to machine learning/deep learning research. Here we will apply an LSTM autoencoder (AE) to identify ECG anomaly detections. In our experiments,…

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Semi-supervised learning via Compact Latent Space Clustering

Implementation for our paper 'Learning Guided Convolutional Network for Depth Completion'

[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)

Code for the intrinsic dimensionality estimate of data representations

[ICLR 2022] "As-ViT: Auto-scaling Vision Transformers without Training" by Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou

[ICCV2019] Boundary-Aware Feature Propagation for Scene Segmentation

Nvidia Semantic Segmentation monorepo

Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation, CVPR 2019

A self-supervised learning framework for audio-visual speech

Deep Learning sample programs using PyTorch in C++

Semantic Segmentation published in Kroc 2019 & Side Project

Global Reasoning module for visual recognition

Apache 2.0 License

Cracking the Coding Interview in Python 3. The solutions all have detailed explanations with visuals.

Related papers and codes for vision-based robotic grasping

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation