Stars
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
TPAMI2023 & CVPR2022 - Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning & Learn From Others and Be Yourself in Heterogeneous Federated Learning
Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data
CVPR2023 - Rethinking Federated Learning with Domain Shift: A Prototype View
The code repository for "Co-Transport for Class-Incremental Learning" (ACM MM'21) in PyTorch.
Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.
Code for "Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning"
PyTorch implementation of our NeurIPS 2021 paper "Class-Incremental Learning via Dual Augmentation"
This is the formal code implementation of the CVPR 2022 paper 'Federated Class Incremental Learning'.
An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.
[CVPR2024] FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning
The code repository for "Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration" (NeurIPS'23) in PyTorch
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
Implementation of Learning without Forgetting paper
PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"
The open-souce code of FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data, accepted by IEEE TMC.
Self-supervised Federated Learning for Medical Imaging - IEEE TMI
[ICCV 2023] FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation
The is the official implementation of ICCV 2023 paper "No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier".
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
The source code and collected data for the Meta-HAR (WWW 2021) paper.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image