mlsanityData to 14 Oct 2026

PyCIL: A Python Toolbox for Class-Incremental Learning

arXiv 2112.12533 ↗First posted 23 Dec 2021cs.LG cs.CVcited by 83

Not on the map. Why?

Abstract (arXiv)

Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process. However, real-world applications often face the incoming new classes, and a model should incorporate them continually. The learning paradigm is called Class-Incremental Learning (CIL). We propose a Python toolbox that implements several key algorithms for class-incremental learning to ease the burden of researchers in the machine learning community. The toolbox contains implementations of a number of founding works of CIL such as EWC and iCaRL, but also provides current state-of-the-art algorithms that can be used for conducting novel fundamental research. This toolbox, named PyCIL for Python Class-Incremental Learning, is available at https://github.com/G-U-N/PyCIL

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

16 of 30 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2016Learning without Forgettingcited by 2,496
  6. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  7. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  8. 2019Large Scale Incremental Learningcited by 732
  9. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  10. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 283
  11. 2015MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systemscited by 195
  12. 2021Learning Placeholders for Open-Set Recognitioncited by 121
4 more
  1. 2018Open-world Learning and Application to Product Classificationcited by 39
  2. 2021Co-Transport for Class-Incremental Learningcited by 38
  3. 2020AliCoCo: Alibaba E-commerce Cognitive Concept Netcited by 23
  4. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 20; 2024: 24; 2025: 19; 2026: 14.

83 papers.

Sort:

By area:

  1. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  2. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 229
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 184
  5. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 154
  6. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoisingcited by 139
  7. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  8. 2024Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learningcited by 117
  9. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  10. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 87
  11. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  12. 2023PILOT: A Pre-Trained Model-Based Continual Learning Toolboxcited by 64
38 more
  1. 2023TiC-CLIP: Continual Training of CLIP Modelscited by 38
  2. 2024Divide and not forget: Ensemble of selectively trained experts in Continual Learningcited by 38
  3. 2024Make Continual Learning Stronger via C-Flatcited by 35
  4. 2024Resurrecting Old Classes with New Data for Exemplar-Free Continual Learningcited by 33
  5. 2024Exemplar-free Continual Representation Learning via Learnable Drift Compensationcited by 31
  6. 2023Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learningcited by 26
  7. 2023Dynamic Residual Classifier for Class Incremental Learningcited by 26
  8. 2023Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learningcited by 18
  9. 2024Revisiting Neural Networks for Continual Learning: An Architectural Perspectivecited by 17
  10. 2023Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learningcited by 16
  11. 2023Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgerycited by 15
  12. 2025Task-Agnostic Guided Feature Expansion for Class-Incremental Learningcited by 15
  13. 2024Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learningcited by 14
  14. 2025Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspectivecited by 14
  15. 2025On the Computation of the Fisher Information in Continual Learningcited by 13
  16. 2025MCITlib: Multimodal Continual Instruction Tuning Library and Benchmarkcited by 13
  17. 2024Hyperparameters in Continual Learning: A Reality Checkcited by 12
  18. 2025Forget Forgetting: Continual Learning in a World of Abundant Memorycited by 11
  19. 2024iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learningcited by 10
  20. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 8
  21. 2026FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamicscited by 8
  22. 2022Progressive Learning without Forgettingcited by 7
  23. 2025Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learningcited by 7
  24. 2024REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learningcited by 6
  25. 2023Category Adaptation Meets Projected Distillation in Generalized Continual Category Discoverycited by 5
  26. 2023Looking through the past: better knowledge retention for generative replay in continual learningcited by 4
  27. 2023Continual Adversarial Defensecited by 4
  28. 2024Future-Proofing Class-Incremental Learningcited by 4
  29. 2024Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyondcited by 4
  30. 2025Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifoldscited by 4
  31. 2023Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learningcited by 3
  32. 2026C3Box: A CLIP-based Class-Incremental Learning Toolboxcited by 3
  33. 2026Elastic Weight Consolidation Done Right for Continual Learningcited by 3
  34. 2023AdaCL:Adaptive Continual Learningcited by 2
  35. 2023Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learningcited by 2
  36. 2024Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learningcited by 2
  37. 2025OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensingcited by 2
  38. 2025EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learningcited by 2

50 most cited of 83 All 83 (JSON)