.. _Awesome Papers Using PyCIL:

Awesome Papers using PyCIL
====================

Our Papers
-------------

- Class-Incremental Learning: A Survey (**TPAMI 2024**) `[paper] <https://arxiv.org/abs/2302.03648>`_   `[code] <https://github.com/zhoudw-zdw/CIL_Survey/>`_  
  
- Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning (**CVPR 2024**) `[paper] <https://arxiv.org/abs/2403.12030>`_  `[code] <https://github.com/sun-hailong/CVPR24-Ease>`_  

- Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning (**ICML 2024**) `[paper] <https://openreview.net/forum?id=aksdU1KOpT>`_   `[code] <https://github.com/bwnzheng/MRFA_ICML2024>`_  

- Continual Learning with Pre-Trained Models: A Survey (**IJCAI 2024**) `[paper] <https://arxiv.org/abs/2401.16386>`_   `[code] <https://github.com/sun-hailong/LAMDA-PILOT>`_  

- Learning without Forgetting for Vision-Language Models (**arXiv 2023**) `[paper] <https://arxiv.org/abs/2305.19270>`_  

- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (**arXiv 2023**) `[paper] <https://arxiv.org/abs/2303.07338>`_   `[code] <https://github.com/zhoudw-zdw/RevisitingCIL>`_  

- PILOT: A Pre-Trained Model-Based Continual Learning Toolbox (**arXiv 2023**) `[paper] <https://arxiv.org/abs/2309.07117>`_   `[code] <https://github.com/sun-hailong/LAMDA-PILOT>`_  

- Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration (**NeurIPS 2023**) `[paper] <https://arxiv.org/abs/2312.05229>`_    `[Code] <https://github.com/wangkiw/TEEN>`_

- BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion (**ICLR 2023**) `[paper] <https://openreview.net/forum?id=iP77_axu0h3>`_   `[code] <https://github.com/G-U-N/ICLR23-BEEF/>`_  

- A model or 603 exemplars: Towards memory-efficient class-incremental learning (**ICLR 2023**) `[paper] <https://arxiv.org/abs/2205.13218>`_   `[code] <https://github.com/wangkiw/ICLR23-MEMO/>`_  

- Few-shot class-incremental learning by sampling multi-phase tasks (**TPAMI 2022**) `[paper] <https://arxiv.org/pdf/2203.17030.pdf>`_   `[code] <https://github.com/zhoudw-zdw/TPAMI-Limit>`_  

- Foster: Feature Boosting and Compression for Class-incremental Learning (**ECCV 2022**) `[paper] <https://arxiv.org/abs/2204.04662>`_   `[code] <https://github.com/G-U-N/ECCV22-FOSTER/>`_  

- Forward compatible few-shot class-incremental learning (**CVPR 2022**) `[paper] <https://openaccess.thecvf.com/content/CVPR2022/papers/Zhou_Forward_Compatible_Few-Shot_Class-Incremental_Learning_CVPR_2022_paper.pdf>`_   `[code] <https://github.com/zhoudw-zdw/CVPR22-Fact>`_  

- Co-Transport for Class-Incremental Learning (**ACM MM 2021**) `[paper] <https://arxiv.org/abs/2107.12654>`_   `[code] <https://github.com/zhoudw-zdw/MM21-Coil>`_  

Other Awesome Works
----------------------

- Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint (**ICCV 2023**) `[paper] <https://openaccess.thecvf.com/content/ICCV2023/papers/Chavan_Towards_Realistic_Evaluation_of_Industrial_Continual_Learning_Scenarios_with_an_ICCV_2023_paper.pdf>`_`[code] <https://github.com/Vivek9Chavan/RECIL>`_

- Dynamic Residual Classifier for Class Incremental Learning (**ICCV 2023**) `[paper] <https://openaccess.thecvf.com/content/ICCV2023/papers/Chen_Dynamic_Residual_Classifier_for_Class_Incremental_Learning_ICCV_2023_paper.pdf>`_`[code] <https://github.com/chen-xw/DRC-CIL>`_

- S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning (**NeurIPS 2022**) `[paper] <https://openreview.net/forum?id=ZVe_WeMold>`_`[code] <https://github.com/iamwangyabin/S-Prompts>`_