NeurAI-Lab / CLS-ER
The official PyTorch code for ICLR'22 Paper "Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System""
☆47Updated last year
Alternatives and similar repositories for CLS-ER:
Users that are interested in CLS-ER are comparing it to the libraries listed below
- Co^2L: Contrastive Continual Learning (ICCV2021)☆92Updated 2 years ago
- Code for the paper "Representational Continuity for Unsupervised Continual Learning" (ICLR 22)☆95Updated 2 years ago
- Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality (NeurIPS 2023, Spotlight)☆81Updated 3 months ago
- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (IJCV 2024)☆132Updated 6 months ago
- ☆63Updated 3 years ago
- Codebase for Continual Prototype Evolution (CoPE) to attain perpetually representative prototypes for online and non-stationary datastrea…☆44Updated 2 years ago
- PyTorch implementation of our NeurIPS 2021 paper "Class-Incremental Learning via Dual Augmentation"☆36Updated 2 years ago
- ☆29Updated last year
- Code Implementation for CVPR 2023 Paper: Class-Incremental Exemplar Compression for Class-Incremental Learning☆24Updated last year
- PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"☆107Updated last year
- RanPAC: Random Projections and Pre-trained Models for Continual Learning - Official code repository for NeurIPS 2023 Published Paper☆43Updated 2 weeks ago
- [CVPR 2023] Regularizing Second-Order Influences for Continual Learning☆34Updated last year
- ☆29Updated last year
- The code repository for "A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning" (ICLR'23) in PyTorch☆41Updated last year
- Official repository for the paper "Self-Supervised Models are Continual Learners" (CVPR 2022)☆121Updated 2 years ago
- Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning