Official code for paper "OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learning"

Official PyTorch Implementation of PuriDivER CVPR 2022.

Class Incremental Learning (iCaRL, EEIL, BiC) reproduce github repository.

Code for SCIENTIA SINICA Informationis paper "Generalized representation of local relationships for few-shot incremental learning", 局部关系泛化表征的小样本增量学习

Official code for "Weighted Ensemble Models Are Strong Continual Learners"

The official code for our paper "Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants".

The code repository for "Co-Transport for Class-Incremental Learning" (ACM MM'21) in PyTorch.

Official Implementation of the paper "Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation"

Official Implementation of CVPR 2022 workshop paper "CNLL: A Semi-supervised Approach for Continual Noisy Label Learning"

Official implementation for CIGN

Official Implementation of the ECCV 2022 Paper "Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer"

✌[ICLR 2024] Class Incremental Learning via Likelihood Ratio Based Task Prediction

(AAAI 2021) Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network

Code for the ICLR2022 paper on Subspace Regularization for few-shot class incremental image classification

ICLR2024 paper on Continual Learning

[AAAI 2022 Oral] Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection

The code repository for "Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks" (TPAMI 2023) in PyTorch.

The code repository for "A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning" (ICLR'23) in PyTorch

The official implementation for ECCV22 paper: "FOSTER: Feature Boosting and Compression for Class-Incremental Learning" in PyTorch.

PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).