Mattdl / ContinualPrototypeEvolution
Codebase for Continual Prototype Evolution (CoPE) to attain perpetually representative prototypes for online and non-stationary datastreams. Includes implementation of the Pseudo-Prototypical Proxy (PPP) loss.
☆43Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for ContinualPrototypeEvolution
- Co^2L: Contrastive Continual Learning (ICCV2021)☆89Updated 2 years ago
- Code for the paper "Representational Continuity for Unsupervised Continual Learning" (ICLR 22)☆93Updated last year
- PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (…☆73Updated last year
- PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"☆104Updated last year
- ☆35Updated 2 years ago
- Code to reproduce the experiments of "Rethinking Experience Replay: a Bag of Tricks for Continual Learning"☆43Updated last year
- ☆29Updated last year
- ☆19Updated 2 years ago
- Official repository for the paper "Self-Supervised Models are Continual Learners" (CVPR 2022)☆116Updated 2 years ago
- Official repository of the paper 'Essentials for Class Incremental Learning'☆40Updated 3 years ago
- ☆53Updated 2 years ago
- Code for our CVPR 2022 workshop paper "Towards Exemplar-Free Continual Learning in Vision Transformers"☆21Updated 2 years ago
- Source code for "Gradient Based Memory Editing for Task-Free Continual Learning", 4th Lifelong ML Workshop@ICML 2020☆17Updated last year
- PyTorch implementation of our NeurIPS 2021 paper "Class-Incremental Learning via Dual Augmentation"☆33Updated 2 years ago
- PyTorch code for the ICCV'21 paper: "Always Be Dreaming: A New Approach for Class-Incremental Learning"☆60Updated 2 years ago
- The official PyTorch code for 'DER: Dynamically Expandable Representation for Class Incremental Learning' accepted by CVPR2021☆155Updated 3 years ago
- Code for CVPR2022 paper "Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency"☆23Updated 2 years ago
- Generative Feature Replay For Class-Incremental Learning☆36Updated 4 years ago
- Code Implementation for CVPR 2023 Paper: Class-Incremental Exemplar Compression for Class-Incremental Learning☆24Updated last year
- ☆63Updated 2 years ago
- ☆35Updated 3 years ago
- ☆22Updated 2 years ago
- ☆58Updated 2 years ago
- Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning☆24Updated last year
- Official implementation of "On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning"☆15Updated 2 years ago
- Code for "A Comprehensive Empirical Evaluation on Online Continual Learning" ICCVW 2023 VCL Workshop☆37Updated 7 months ago
- Official codebase of the "Rehearsal revealed:The limits and merits of revisiting samples in continual learning" paper.☆27Updated 3 years ago
- This is a public repository for:☆38Updated 3 years ago
- The code repository for "A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning" (ICLR'23) in PyTorch☆39Updated last year
- Continual / incremental / lifelong learning methods implemented by PyTorch. Especially the methods based on memory replay.☆49Updated last year