CoChat
Sign Up
Cited by 376Domain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsData Stream Mining Techniques

Class-Incremental Learning: A Survey

Open access
Zhou, Da-Wei, Wang, Qi-Wei, Qi, Zhi-Hong, Ye, Han-Jia, Zhan, De-Chuan, Liu, Ziwei·2024·IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/tpami.2024.3429383
Open this paper in CoChat — free accountOpen PDF

Abstract

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs - the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in class-incremental learning and summarize these methods from several aspects. We also provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2024.3429383

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 268

  1. Quan Feng and Songcan Chen. Learning multi-tasks with inconsistent labels by using auxiliary big task. Frontiers of Computer Science, 17(5):175342, 2023.
  2. Heitor Murilo Gomes, Jean Paul Barddal, Fabrício Enembreck, and Albert Bifet. A survey on ensemble learning for data stream classification. ACM Computing Surveys, 50(2):1-36, 2017.
  3. Georg Krempl, Indre Žliobaite, Dariusz Brzeziński, Eyke Hüllermeier, Mark Last, Vincent Lemaire, Tino Noack, Ammar Shaker, Sonja Sievi, Myra Spiliopoulou, et al. Open challenges for data stream mining research. KDD, 16(1):1-10, 2014.
  4. Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Aleš Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence, 44(7):3366- 3385, 2021.
  5. Stephen T Grossberg. Studies of mind and brain: Neural principles of learning, perception, development, cognition, and motor control, volume 70. Springer Science & Business Media, 2012.
  6. Gido M van de Ven, Tinne Tuytelaars, and Andreas S Tolias. Three types of incremental learning. Nature Machine Intelligence, pages 1-13, 2022.
  7. Zhiyuan Chen and Bing Liu. Lifelong machine learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 12(3):1-207, 2018.
  8. Jie Lu, Anjin Liu, Fan Dong, Feng Gu, Joao Gama, and Guangquan Zhang. Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 31(12):2346-2363, 2018.
  9. Zhi-Hua Zhou, Jianxin Wu, and Wei Tang. Ensembling neural networks: many could be better than all. Artificial intelligence, 137(1-2):239-263, 2002.
  10. Ilja Kuzborskij, Francesco Orabona, and Barbara Caputo. From n to n+ 1: Multiclass transfer incremental learning. In CVPR, pages 3358-3365, 2013.
  11. Qing Da, Yang Yu, and Zhi-Hua Zhou. Learning with augmented class by exploiting unlabeled data. In AAAI, pages 1760-1766, 2014.
  12. Marc Masana, Xialei Liu, Bartłomiej Twardowski, Mikel Menta, An- drew D Bagdanov, and Joost Van De Weijer. Class-incremental learning: survey and performance evaluation on image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5):5513- 5533, 2022.
  13. Shipeng Yan, Jiangwei Xie, and Xuming He. Der: Dynamically expandable representation for class incremental learning. In CVPR, pages 3014-3023, 2021.
  14. Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. Foster: Feature boosting and compression for class-incremental learning. In ECCV, pages 398-414, 2022.
  15. Da-Wei Zhou, Qi-Wei Wang, Han-Jia Ye, and De-Chuan Zhan. A model or 603 exemplars: Towards memory-efficient class-incremental learning. In ICLR, 2023.
  16. Arthur Douillard, Alexandre Ramé, Guillaume Couairon, and Matthieu Cord. Dytox: Transformers for continual learning with dynamic token expansion. In CVPR, pages 9285-9295, 2022.
  17. Magdalena Marta Biesialska, Katarzyna Biesialska, and Marta Ruiz Costa-Jussà. Continual lifelong learning in natural language processing: a survey. In COLING, pages 6523-6541, 2020.
  18. German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. Continual lifelong learning with neural networks: A review. Neural Networks, 113:54-71, 2019.
  19. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.
  20. Jihwan Bang, Heesu Kim, YoungJoon Yoo, Jung-Woo Ha, and Jonghyun Choi. Rainbow memory: Continual learning with a memory of diverse samples. In CVPR, pages 8218-8227, 2021.
  21. Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, and Yihong Gong. Few-shot class-incremental learning. In CVPR, pages 12183-12192, 2020.
  22. Xialei Liu, Yu-Song Hu, Xu-Sheng Cao, Andrew D Bagdanov, Ke Li, and Ming-Ming Cheng. Long-tailed class incremental learning. In ECCV, pages 495-512, 2022.
  23. Zheda Mai, Ruiwen Li, Hyunwoo Kim, and Scott Sanner. Supervised contrastive replay: Revisiting the nearest class mean classifier in online class-incremental continual learning. In CVPR, pages 3589-3599, 2021.
  24. Rudolf Kruse, Sanaz Mostaghim, Christian Borgelt, Christian Braune, and Matthias Steinbrecher. Multi-layer perceptrons. In Computational intelligence: a methodological introduction, pages 53-124. 2022.
  25. Yann LeCun, Koray Kavukcuoglu, and Clément Farabet. Convolutional networks and applications in vision. In ISCAS, pages 253-256, 2010.
  26. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, pages 5998-6008, 2017.
  27. Rahaf Aljundi, Min Lin, Baptiste Goujaud, and Yoshua Bengio. Gradient based sample selection for online continual learning. In NeurIPS, pages 11816-11825, 2019.
  28. David Isele and Akansel Cosgun. Selective experience replay for lifelong learning. In AAAI, pages 3302-3309, 2018.
  29. Arslan Chaudhry, Albert Gordo, Puneet Kumar Dokania, Philip Torr, and David Lopez-Paz. Using hindsight to anchor past knowledge in continual learning. In AAAI, pages 6993-7001, 2020.
  30. Matthias De Lange and Tinne Tuytelaars. Continual prototype evolution: Learning online from non-stationary data streams. In ICCV, pages 8250-8259, 2021.
  31. Ahmet Iscen, Jeffrey Zhang, Svetlana Lazebnik, and Cordelia Schmid. Memory-efficient incremental learning through feature adaptation. In ECCV, pages 699-715, 2020.
  32. Hanbin Zhao, Hui Wang, Yongjian Fu, Fei Wu, and Xi Li. Memory- efficient class-incremental learning for image classification. IEEE Transactions on Neural Networks and Learning Systems, 33(10):5966- 5977, 2021.
  33. Yaoyao Liu, Yuting Su, An-An Liu, Bernt Schiele, and Qianru Sun. Mnemonics training: Multi-class incremental learning without forgetting. In CVPR, pages 12245-12254, 2020.
  34. Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. Continual learning with deep generative replay. In NIPS, pages 2990-2999, 2017.
  35. Chen He, Ruiping Wang, Shiguang Shan, and Xilin Chen. Exemplar- supported generative reproduction for class incremental learning. In BMVC, page 98, 2018.
  36. Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao, Jinwen Ma, Dongyan Zhao, and Rui Yan. Overcoming catastrophic forgetting for continual learning via model adaptation. In ICLR, 2019.
  37. Ronald Kemker and Christopher Kanan. Fearnet: Brain-inspired model for incremental learning. In ICLR, 2018.
  38. Oleksiy Ostapenko, Mihai Puscas, Tassilo Klein, Patrick Jahnichen, and Moin Nabi. Learning to remember: A synaptic plasticity driven framework for continual learning. In CVPR, pages 11321-11329, 2019.
  39. Ye Xiang, Ying Fu, Pan Ji, and Hua Huang. Incremental learning using conditional adversarial networks. In ICCV, pages 6619-6628, 2019.
  40. Liyuan Wang, Kuo Yang, Chongxuan Li, Lanqing Hong, Zhenguo Li, and Jun Zhu. Ordisco: Effective and efficient usage of incremental unlabeled data for semi-supervised continual learning. In CVPR, pages 5383-5392, 2021.
  41. Jian Jiang, Edoardo Cetin, and Oya Celiktutan. Ib-drr-incremental learning with information-back discrete representation replay. In CVPRW, pages 3533-3542, 2021.
  42. Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, and Cheng-Lin Liu. Prototype augmentation and self-supervision for incremental learning. In CVPR, pages 5871-5880, 2021.
  43. Grégoire Petit, Adrian Popescu, Hugo Schindler, David Picard, and Bertrand Delezoide. Fetril: Feature translation for exemplar-free class- incremental learning. In WACV, pages 3911-3920, 2023.
  44. Quentin Jodelet, Xin Liu, Yin Jun Phua, and Tsuyoshi Murata. Class- incremental learning using diffusion model for distillation and replay. In ICCVW, pages 3425-3433, 2023.
  45. Rui Gao and Weiwei Liu. Ddgr: continual learning with deep diffusion- based generative replay. In ICML, pages 10744-10763, 2023.
  46. David Lopez-Paz and Marc'Aurelio Ranzato. Gradient episodic memory for continual learning. In NeurIPS, pages 6467-6476, 2017.
  47. Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, and Mo- hamed Elhoseiny. Efficient lifelong learning with a-gem. In ICLR, 2018.
  48. Shipeng Wang, Xiaorong Li, Jian Sun, and Zongben Xu. Training networks in null space of feature covariance for continual learning. In CVPR, pages 184-193, 2021.
  49. Shixiang Tang, Dapeng Chen, Jinguo Zhu, Shijie Yu, and Wanli Ouyang. Layerwise optimization by gradient decomposition for continual learning. In CVPR, pages 9634-9643, 2021.
  50. Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, and Gerald Tesauro. Learning to learn without forgetting by maximizing transfer and minimizing interference. In ICLR, 2018.
  51. Jaehong Yoon, Eunho Yang, Jeongtae Lee, and Sung Ju Hwang. Lifelong learning with dynamically expandable networks. In ICLR, 2018.
  52. Ju Xu and Zhanxing Zhu. Reinforced continual learning. In NeurIPS, pages 899-908, 2018.
  53. Xilai Li, Yingbo Zhou, Tianfu Wu, Richard Socher, and Caiming Xiong. Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting. In ICML, pages 3925-3934, 2019.
  54. Andrei A Rusu, Neil C Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. Progressive neural networks. arXiv preprint arXiv:1606.04671, 2016. · arXiv
  55. Rahaf Aljundi, Punarjay Chakravarty, and Tinne Tuytelaars. Expert gate: Lifelong learning with a network of experts. In CVPR, pages 3366-3375, 2017.
  56. Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, and Raia Hadsell. Progress & compress: A scalable framework for continual learning. In ICML, pages 4528-4537, 2018.
  57. Hanbin Zhao, Yongjian Fu, Mintong Kang, Qi Tian, Fei Wu, and Xi Li. Mgsvf: Multi-grained slow vs. fast framework for few-shot class-incremental learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(3):1576-1588, 2024.
  58. Yaoyao Liu, Bernt Schiele, and Qianru Sun. Adaptive aggregation networks for class-incremental learning. In CVPR, pages 2544-2553, 2021.
  59. Quang Pham, Chenghao Liu, and Steven Hoi. Dualnet: Continual learning, fast and slow. NeurIPS, 34:16131-16144, 2021.
  60. Fu-Yun Wang, Da-Wei Zhou, Liu Liu, Han-Jia Ye, Yatao Bian, De-Chuan Zhan, and Peilin Zhao. Beef: Bi-compatible class-incremental learning via energy-based expansion and fusion. In ICLR, 2023.
  61. Zifeng Wang, Zizhao Zhang, Chen-Yu Lee, Han Zhang, Ruoxi Sun, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, and Tomas Pfister. Learning to prompt for continual learning. In CVPR, pages 139-149, 2022.
  62. Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi, Ruoxi Sun, Han Zhang, Chen-Yu Lee, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, et al. Dualprompt: Complementary prompting for rehearsal-free continual learning. In ECCV, pages 631-648, 2022.
  63. James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante- Bonilla, Donghyun Kim, Assaf Arbelle, Rameswar Panda, Rogerio Feris, and Zsolt Kira. Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. In CVPR, pages 11909- 11919, 2023.
  64. Yabin Wang, Zhiwu Huang, and Xiaopeng Hong. S-prompts learning with pre-trained transformers: An occam's razor for domain incremental learning. NeurIPS, pages 5682-5695, 2022.
  65. Friedemann Zenke, Ben Poole, and Surya Ganguli. Continual learning through synaptic intelligence. In ICML, pages 3987-3995, 2017.
  66. Rahaf Aljundi, Klaas Kelchtermans, and Tinne Tuytelaars. Task-free continual learning. In CVPR, pages 11254-11263, 2019.
  67. Sang-Woo Lee, Jin-Hwa Kim, Jaehyun Jun, Jung-Woo Ha, and Byoung- Tak Zhang. Overcoming catastrophic forgetting by incremental moment matching. In NIPS, pages 4652-4662, 2017.
  68. Yang Yang, Da-Wei Zhou, De-Chuan Zhan, Hui Xiong, Yuan Jiang, and Jian Yang. Cost-effective incremental deep model: Matching model capacity with the least sampling. IEEE Transactions on Knowledge and Data Engineering, 35(4):3575-3588, 2021.
  69. Janghyeon Lee, Hyeong Gwon Hong, Donggyu Joo, and Junmo Kim. Continual learning with extended kronecker-factored approximate curvature. In CVPR, pages 9001-9010, 2020.
  70. Zhizhong Li and Derek Hoiem. Learning without forgetting. In ECCV, pages 614-629, 2016.
  71. Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Fu. Large scale incremental learning. In CVPR, pages 374-382, 2019.
  72. Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, and Dahua Lin. Lifelong learning via progressive distillation and retrospection. In ECCV, pages 437-452, 2018.
  73. Kibok Lee, Kimin Lee, Jinwoo Shin, and Honglak Lee. Overcoming catastrophic forgetting with unlabeled data in the wild. In ICCV, pages 312-321, 2019.
  74. Junting Zhang, Jie Zhang, Shalini Ghosh, Dawei Li, Serafettin Tasci, Larry Heck, Heming Zhang, and C-C Jay Kuo. Class-incremental learning via deep model consolidation. In WACV, pages 1131-1140, 2020.
  75. James Smith, Yen-Chang Hsu, Jonathan Balloch, Yilin Shen, Hongxia Jin, and Zsolt Kira. Always be dreaming: A new approach for data-free class-incremental learning. In ICCV, pages 9374-9384, 2021.
  76. Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. Co-transport for class- incremental learning. In ACM MM, pages 1645-1654, 2021.
  77. Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, and Dahua Lin. Learning a unified classifier incrementally via rebalancing. In CVPR, pages 831-839, 2019.
  78. Yichen Lu, Mei Wang, and Weihong Deng. Augmented geometric distillation for data-free incremental person reid. In CVPR, pages 7329- 7338, 2022.
  79. Jaeyoo Park, Minsoo Kang, and Bohyung Han. Class-incremental learning for action recognition in videos. In ICCV, pages 13698-13707, 2021.
  80. Prithviraj Dhar, Rajat Vikram Singh, Kuan-Chuan Peng, Ziyan Wu, and Rama Chellappa. Learning without memorizing. In CVPR, pages 5138-5146, 2019.
  81. Minsoo Kang, Jaeyoo Park, and Bohyung Han. Class-incremental learning by knowledge distillation with adaptive feature consolidation. In CVPR, pages 16071-16080, 2022.
  82. Arthur Douillard, Matthieu Cord, Charles Ollion, Thomas Robert, and Eduardo Valle. Podnet: Pooled outputs distillation for small-tasks incremental learning. In ECCV, pages 86-102, 2020.
  83. Xinting Hu, Kaihua Tang, Chunyan Miao, Xian-Sheng Hua, and Hanwang Zhang. Distilling causal effect of data in class-incremental learning. In CVPR, pages 3957-3966, 2021.
  84. Christian Simon, Piotr Koniusz, and Mehrtash Harandi. On learning the geodesic path for incremental learning. In CVPR, pages 1591-1600, 2021.
  85. Heechul Jung, Jeongwoo Ju, Minju Jung, and Junmo Kim. Less-forgetful learning for domain expansion in deep neural networks. In AAAI, pages 3358-3365, 2018.
  86. Qiankun Gao, Chen Zhao, Bernard Ghanem, and Jian Zhang. R-DFCIL: relation-guided representation learning for data-free class incremental learning. In ECCV, pages 423-439, 2022.
  87. Songlin Dong, Xiaopeng Hong, Xiaoyu Tao, Xinyuan Chang, Xing Wei, and Yihong Gong. Few-shot class-incremental learning via relation knowledge distillation. In AAAI, pages 1255-1263, 2021.
  88. Yu Liu, Xiaopeng Hong, Xiaoyu Tao, Songlin Dong, Jingang Shi, and Yihong Gong. Model behavior preserving for class-incremental learning. IEEE Transactions on Neural Networks and Learning Systems, 34(10):7529-7540, 2023.
  89. Nader Asadi, MohammadReza Davari, Sudhir Mudur, Rahaf Aljundi, and Eugene Belilovsky. Prototype-sample relation distillation: towards replay-free continual learning. In ICML, pages 1093-1106, 2023.
  90. Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma, Shiliang Pu, and De- Chuan Zhan. Forward compatible few-shot class-incremental learning. In CVPR, pages 9046-9056, 2022.
  91. Lu Yu, Bartlomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, and Joost van de Weijer. Semantic drift compensation for class-incremental learning. In CVPR, pages 6982-6991, 2020.
  92. Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip HS Torr, Song Bai, and Vincent YF Tan. Mimicking the oracle: An initial phase decorrelation approach for class incremental learning. In CVPR, pages 16722-16731, 2022.
  93. Shibo Jie, Zhi-Hong Deng, and Ziheng Li. Alleviating representational shift for continual fine-tuning. In CVPRW, pages 3810-3819, 2022.
  94. Pravendra Singh, Vinay Kumar Verma, Pratik Mazumder, Lawrence Carin, and Piyush Rai. Calibrating cnns for lifelong learning. In NeurIPS, pages 15579-15590, 2020.
  95. Pravendra Singh, Pratik Mazumder, Piyush Rai, and Vinay P Namboodiri. Rectification-based knowledge retention for continual learning. In CVPR, pages 15282-15291, 2021.
  96. Francisco M Castro, Manuel J Marín-Jiménez, Nicolás Guil, Cordelia Schmid, and Karteek Alahari. End-to-end incremental learning. In ECCV, pages 233-248, 2018.
  97. Bowen Zhao, Xi Xiao, Guojun Gan, Bin Zhang, and Shu-Tao Xia. Maintaining discrimination and fairness in class incremental learning. In CVPR, pages 13208-13217, 2020.
  98. Hongjoon Ahn, Jihwan Kwak, Subin Lim, Hyeonsu Bang, Hyojun Kim, and Taesup Moon. Ss-il: Separated softmax for incremental learning. In ICCV, pages 844-853, 2021.
  99. Federico Pernici, Matteo Bruni, Claudio Baecchi, Francesco Turchini, and Alberto Del Bimbo. Class-incremental learning with pre-allocated fixed classifiers. In ICPR, pages 6259-6266, 2021.
  100. Chi Zhang, Nan Song, Guosheng Lin, Yun Zheng, Pan Pan, and Yinghui Xu. Few-shot incremental learning with continually evolved classifiers. In CVPR, pages 12455-12464, 2021.
  101. Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan, and Ziwei Liu. Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need. arXiv preprint arXiv:2303.07338, 2023. · arXiv
  102. Mark D McDonnell, Dong Gong, Amin Parveneh, Ehsan Abbasnejad, and Anton van den Hengel. Ranpac: Random projections and pre-trained models for continual learning. In NeurIPS, 2023.
  103. Dipam Goswami, Yuyang Liu, Bartłomiej Twardowski, and Joost van de Weijer. Fecam: Exploiting the heterogeneity of class distributions in exemplar-free continual learning. In NeurIPS, 2023.
  104. Qi-Wei Wang, Da-Wei Zhou, Yi-Kai Zhang, De-Chuan Zhan, and Han- Jia Ye. Few-shot class-incremental learning via training-free prototype calibration. In NeurIPS, 2023.
  105. Wuxuan Shi and Mang Ye. Prototype reminiscence and augmented asymmetric knowledge aggregation for non-exemplar class-incremental learning. In ICCV, pages 1772-1781, 2023.
  106. Da-Wei Zhou, Han-Jia Ye, Liang Ma, Di Xie, Shiliang Pu, and De-Chuan Zhan. Few-shot class-incremental learning by sampling multi-phase tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11):12816-12831, 2023.
  107. Kun Wei, Cheng Deng, Xu Yang, and Maosen Li. Incremental embedding learning via zero-shot translation. In AAAI, pages 10254-10262, 2021.
  108. Gido M Van De Ven, Zhe Li, and Andreas S Tolias. Class-incremental learning with generative classifiers. In CVPRW, pages 3611-3620, 2021.
  109. Max Welling. Herding dynamical weights to learn. In ICML, pages 1121-1128, 2009.
  110. Matthew A Wilson and Bruce L McNaughton. Reactivation of hippocampal ensemble memories during sleep. Science, 265(5172):676- 679, 1994.
  111. Arielle Tambini and Lila Davachi. Persistence of hippocampal multivoxel patterns into postencoding rest is related to memory. Proceedings of the National Academy of Sciences, 110(48):19591-19596, 2013.
  112. Daniel N Barry and Bradley C Love. A neural network account of memory replay and knowledge consolidation. Cerebral Cortex, 33(1):83- 95, 2023.
  113. Roger Ratcliff. Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychological review, 97(2):285, 1990.
  114. Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. In NIPS, pages 4080-4090, 2017.
  115. Arun Mallya and Svetlana Lazebnik. Packnet: Adding multiple tasks to a single network by iterative pruning. In CVPR, pages 7765-7773, 2018.
  116. Jathushan Rajasegaran, Munawar Hayat, Salman Khan, Fahad Shahbaz Khan, and Ling Shao. Random path selection for incremental learning. In NeurIPS, pages 12669-12679, 2019.
  117. Dongmin Park, Seokil Hong, Bohyung Han, and Kyoung Mu Lee. Continual learning by asymmetric loss approximation with single-side overestimation. In ICCV, pages 3335-3344, 2019.
  118. Mohammad Rostami, Soheil Kolouri, and Praveen K Pilly. Complemen- tary learning for overcoming catastrophic forgetting using experience replay. In IJCAI, pages 3339-3345, 2019.
  119. Ching-Yi Hung, Cheng-Hao Tu, Cheng-En Wu, Chien-Hung Chen, Yi- Ming Chan, and Chu-Song Chen. Compacting, picking and growing for unforgetting continual learning. NeurIPS, 32:13669-13679, 2019.
  120. Davide Abati, Jakub Tomczak, Tijmen Blankevoort, Simone Calderara, Rita Cucchiara, and Babak Ehteshami Bejnordi. Conditional channel gated networks for task-aware continual learning. In CVPR, pages 3931-3940, 2020.
  121. KJ Joseph, Jathushan Rajasegaran, Salman Khan, Fahad Shahbaz Khan, and Vineeth N Balasubramanian. Incremental object detection via meta-learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12):9209-9216, 2021.
  122. Jiangpeng He, Runyu Mao, Zeman Shao, and Fengqing Zhu. Incremental learning in online scenario. In CVPR, pages 13926-13935, 2020.
  123. Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, and Simone Calderara. Dark experience for general continual learning: a strong, simple baseline. NeurIPS, 33:15920-15930, 2020.
  124. Ameya Prabhu, Philip HS Torr, and Puneet K Dokania. Gdumb: A simple approach that questions our progress in continual learning. In ECCV, pages 524-540, 2020.
  125. Chris Dongjoo Kim, Jinseo Jeong, and Gunhee Kim. Imbalanced continual learning with partitioning reservoir sampling. In ECCV, pages 411-428, 2020.
  126. Tyler L Hayes and Christopher Kanan. Lifelong machine learning with deep streaming linear discriminant analysis. In CVPRW, pages 220-221, 2020.
  127. Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia, Ales Leonardis, and Tinne Tuytelaars. More classifiers, less forgetting: A generic multi- classifier paradigm for incremental learning. In ECCV, pages 699-716, 2020.
  128. Yaoyao Liu, Bernt Schiele, and Qianru Sun. Rmm: Reinforced memory management for class-incremental learning. NeurIPS, 34:3478-3490, 2021.
  129. Haiyan Yin, Ping Li, et al. Mitigating forgetting in online continual learning with neuron calibration. NeurIPS, 34:10260-10272, 2021.
  130. Rishabh Tiwari, Krishnateja Killamsetty, Rishabh Iyer, and Pradeep Shenoy. Gcr: Gradient coreset based replay buffer selection for continual learning. In CVPR, pages 99-108, 2022.
  131. KJ Joseph, Salman Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, and Vineeth N Balasubramanian. Energy-based latent aligner for incremental learning. In CVPR, pages 7452-7461, 2022.
  132. Jiangwei Xie, Shipeng Yan, and Xuming He. General incremental learning with domain-aware categorical representations. In CVPR, pages 14351-14360, 2022.
  133. Jiahua Dong, Lixu Wang, Zhen Fang, Gan Sun, Shichao Xu, Xiao Wang, and Qi Zhu. Federated class-incremental learning. In CVPR, pages 10164-10173, 2022.
  134. Kai Zhu, Wei Zhai, Yang Cao, Jiebo Luo, and Zheng-Jun Zha. Self- sustaining representation expansion for non-exemplar class-incremental learning. In CVPR, pages 9296-9305, 2022.
  135. Tz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichan- dran, Nuno Vasconcelos, Rahul Bhotika, and Stefano Soatto. Class- incremental learning with strong pre-trained models. In CVPR, pages 9601-9610, 2022.
  136. Beyza Ermis, Giovanni Zappella, Martin Wistuba, Aditya Rawal, and Cedric Archambeau. Memory efficient continual learning with transformers. NeurIPS, pages 10629-10642, 2022.
  137. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In NIPS, pages 2672-2680, 2014.
  138. Diederik P Kingma and Max Welling. Auto-encoding variational bayes. In ICLR, 2014.
  139. Mehdi Mirza and Simon Osindero. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014. · arXiv
  140. Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. NeurIPS, 33:6840-6851, 2020.
  141. Michał Zaj ąc, Kamil Deja, Anna Kuzina, Jakub M Tomczak, Tomasz Trzciński, Florian Shkurti, and Piotr Miłoś. Exploring continual learning of diffusion models. arXiv preprint arXiv:2303.15342, 2023. · arXiv
  142. James Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua, Zsolt Kira, Yilin Shen, and Hongxia Jin. Continual diffusion: Continual customization of text-to-image diffusion with c-lora. arXiv preprint arXiv:2304.06027, 2023. · arXiv
  143. Lukasz Korycki and Bartosz Krawczyk. Class-incremental experience replay for continual learning under concept drift. In CVPR, pages 3649-3658, 2021.
  144. Andrea Maracani, Umberto Michieli, Marco Toldo, and Pietro Zanuttigh. Recall: Replay-based continual learning in semantic segmentation. In ICCV, pages 7026-7035, 2021.
  145. Andrés Villa, Kumail Alhamoud, Victor Escorcia, Fabian Caba, Juan León Alcázar, and Bernard Ghanem. vclimb: A novel video class incremental learning benchmark. In CVPR, pages 19035-19044, 2022.
  146. Eli Verwimp, Matthias De Lange, and Tinne Tuytelaars. Rehearsal revealed: The limits and merits of revisiting samples in continual learning. In ICCV, pages 9385-9394, 2021.
  147. Lorenzo Bonicelli, Matteo Boschini, Angelo Porrello, Concetto Spamp- inato, and Simone Calderara. On the effectiveness of lipschitz-driven rehearsal in continual learning. NeurIPS, pages 31886-31901, 2022.
  148. Longhui Yu, Tianyang Hu, Lanqing Hong, Zhen Liu, Adrian Weller, and Weiyang Liu. Continual learning by modeling intra-class variation. arXiv preprint arXiv:2210.05398, 2022. · arXiv
  149. Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, and Jiashi Feng. Deep long-tailed learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):10795-10816, 2023.
  150. Gido M Van de Ven, Hava T Siegelmann, and Andreas S Tolias. Brain- inspired replay for continual learning with artificial neural networks. Nature communications, 11(1):4069, 2020.
  151. Liyuan Wang, Bo Lei, Qian Li, Hang Su, Jun Zhu, and Yi Zhong. Triple- memory networks: A brain-inspired method for continual learning. IEEE Transactions on Neural Networks and Learning Systems, 33(5):1925- 1934, 2021.
  152. Ryota Yoshihashi, Wen Shao, Rei Kawakami, Shaodi You, Makoto Iida, and Takeshi Naemura. Classification-reconstruction learning for open-set recognition. In CVPR, pages 4016-4025, 2019.
  153. Xialei Liu, Chenshen Wu, Mikel Menta, Luis Herranz, Bogdan Raducanu, Andrew D Bagdanov, Shangling Jui, and Joost van de Weijer. Generative feature replay for class-incremental learning. In CVPRW, pages 226-227, 2020.
  154. Yiduo Guo, Wenpeng Hu, Dongyan Zhao, and Bing Liu. Adaptive orthogonal projection for batch and online continual learning. In AAAI, pages 6783-6791, 2022.
  155. Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta- learning for fast adaptation of deep networks. In ICML, pages 1126-1135, 2017.
  156. Wei-Lun Chao, Han-Jia Ye, De-Chuan Zhan, Mark Campbell, and Kilian Q Weinberger. Revisiting meta-learning as supervised learning. arXiv preprint arXiv:2002.00573, 2020. · arXiv
  157. Jathushan Rajasegaran, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Mubarak Shah. itaml: An incremental task-agnostic meta- learning approach. In CVPR, pages 13588-13597, 2020.
  158. Runqi Wang, Yuxiang Bao, Baochang Zhang, Jianzhuang Liu, Wentao Zhu, and Guodong Guo. Anti-retroactive interference for lifelong learning. In ECCV, pages 163-178, 2022.
  159. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. MIT press, 2016.
  160. Zhi-Hua Zhou. Ensemble methods: foundations and algorithms. CRC press, 2012.
  161. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015. · arXiv
  162. Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge J. Belongie, Bharath Hariharan, and Ser-Nam Lim. Visual prompt tuning. In ECCV, pages 709-727, 2022.
  163. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In ICML, pages 8748-8763, 2021.
  164. Da-Wei Zhou, Hai-Long Sun, Jingyi Ning, Han-Jia Ye, and De-Chuan Zhan. Continual learning with pre-trained models: A survey. In IJCAI, 2024.
  165. Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, and De-Chuan Zhan. Expand- able subspace ensemble for pre-trained model-based class-incremental learning. In CVPR, pages 23554-23564, 2024.
  166. Da-Wei Zhou, Yuanhan Zhang, Jingyi Ning, Han-Jia Ye, De-Chuan Zhan, and Ziwei Liu. Learning without forgetting for vision-language models. arXiv preprint arXiv:2305.19270, 2023. · arXiv
  167. Hyuntak Cha, Jaeho Lee, and Jinwoo Shin. Co2l: Contrastive continual learning. In ICCV, pages 9516-9525, 2021.
  168. Yu-Ming Tang, Yi-Xing Peng, and Wei-Shi Zheng. When prompt-based incremental learning does not meet strong pretraining. In ICCV, pages 1706-1716, 2023.
  169. Oleksiy Ostapenko, Pau Rodriguez, Massimo Caccia, and Laurent Charlin. Continual learning via local module composition. NeurIPS, 34:30298-30312, 2021.
  170. Sylvestre-Alvise Rebuffi, Hakan Bilen, and Andrea Vedaldi. Learning multiple visual domains with residual adapters. In NIPS, pages 506-516, 2017.
  171. Lucien Le Cam. Asymptotic methods in statistical decision theory. Springer Science & Business Media, 2012.
  172. Frederik Benzing. Unifying importance based regularisation methods for continual learning. In AISTATS, pages 2372-2396, 2022.
  173. Thomas Mensink, Jakob Verbeek, Florent Perronnin, and Gabriela Csurka. Distance-based image classification: Generalizing to new classes at near-zero cost. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11):2624-2637, 2013.
  174. Hanbin Zhao, Xin Qin, Shihao Su, Yongjian Fu, Zibo Lin, and Xi Li. When video classification meets incremental classes. In ACM MM, pages 880-889, 2021.
  175. Wonpyo Park, Dongju Kim, Yan Lu, and Minsu Cho. Relational knowledge distillation. In CVPR, pages 3967-3976, 2019.
  176. Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota, Mingli Ding, Moin Nabi, Xavier Alameda-Pineda, and Elisa Ricci. Uncertainty-aware contrastive distillation for incremental semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2):2567- 2581, 2023.
  177. Nan Pu, Wei Chen, Yu Liu, Erwin M Bakker, and Michael S Lew. Lifelong person re-identification via adaptive knowledge accumulation. In CVPR, pages 7901-7910, 2021.
  178. Bowen Zheng, Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. Multi- layer rehearsal feature augmentation for class-incremental learning. In ICML, 2024.
  179. Quang Pham, Chenghao Liu, and HOI Steven. Continual normalization: Rethinking batch normalization for online continual learning. In ICLR, 2022.
  180. Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, pages 448-456, 2015.
  181. Bowen Zheng, Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. Pre- serving locality in vision transformers for class incremental learning. In ICME, pages 1157-1162, 2023.
  182. Guangyuan Shi, Jiaxin Chen, Wenlong Zhang, Li-Ming Zhan, and Xiao- Ming Wu. Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. In NeurIPS, pages 6747-6761, 2021.
  183. Seyed Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, and Hassan Ghasemzadeh. Understanding the role of training regimes in continual learning. NeurIPS, 33:7308-7320, 2020.
  184. Robert M Nosofsky. Attention, similarity, and the identification- categorization relationship. Journal of experimental psychology: General, 115(1):39, 1986.
  185. Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. Manifold mixup: Better representations by interpolating hidden states. In ICML, pages 6438-6447, 2019.
  186. Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, and Dawn Song. Natural adversarial examples. In CVPR, pages 15262-15271, 2021.
  187. Amit Alfassy, Assaf Arbelle, Oshri Halimi, Sivan Harary, Roei Herzig, Eli Schwartz, Rameswar Panda, Michele Dolfi, Christoph Auer, Peter Staar, et al. Feta: Towards specializing foundational models for expert task applications. In NeurIPS, pages 29873-29888, 2022.
  188. Yann LeCun, Sumit Chopra, Raia Hadsell, M Ranzato, and Fujie Huang. A tutorial on energy-based learning. Predicting structured data, 1(0), 2006.
  189. Shuang Li, Yilun Du, Gido van de Ven, and Igor Mordatch. Energy-based models for continual learning. In CoLLAs, pages 1-22, 2022.
  190. Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. Imagenet large scale visual recognition challenge. IJCV, 115(3):211-252, 2015.
  191. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Brad- bury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS, pages 8026-8037, 2019.
  192. Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, and De-Chuan Zhan. Pycil: a python toolbox for class-incremental learning. SCIENCE CHINA Information Sciences, 66(9):197101, 2023.
  193. Stéphane d'Ascoli, Hugo Touvron, Matthew L Leavitt, Ari S Morcos, Giulio Biroli, and Levent Sagun. Convit: Improving vision transformers with soft convolutional inductive biases. In ICML, pages 2286-2296, 2021.
  194. Yi Zhong, Jia-Hui Pan, Haoxin Li, and Wei-Shi Zheng. Weakly supervised action anticipation without object annotations. Frontiers of Computer Science, 17(2):172313, 2023.
  195. Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan. Learning placeholders for open-set recognition. In CVPR, pages 4401-4410, 2021.
  196. Huiping Zhuang, Zhenyu Weng, Run He, Zhiping Lin, and Ziqian Zeng. GKEAL: Gaussian kernel embedded analytic learning for few-shot class incremental task. In CVPR, pages 7746-7755, 2023.
  197. Shipeng Yan, Lanqing Hong, Hang Xu, Jianhua Han, Tinne Tuytelaars, Zhenguo Li, and Xuming He. Generative negative text replay for continual vision-language pretraining. In ECCV, pages 22-38, 2022.
  198. Amanda Rios, Nilesh Ahuja, Ibrahima Ndiour, Utku Genc, Laurent Itti, and Omesh Tickoo. incdfm: Incremental deep feature modeling for continual novelty detection. In ECCV, pages 588-604, 2022.
  199. Abhijit Bendale and Terrance Boult. Towards open world recognition. In CVPR, pages 1893-1902, 2015.
  200. Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, and Sarath Chandar. Iirc: Incremental implicitly-refined classification. In CVPR, pages 11038-11047, 2021.

200 of 268 shown

Cited by

Sorted by citations

Authors
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z.
Affiliations
  • Nanyang Technological University (SG)
  • School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
ORCID
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2024-12
Volume
46
Issue
12
Pages
9851-9873
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
DOI
10.1109/tpami.2024.3429383
OpenAlex
W4400680576
Cited by
376
References
16
Citations by year
2026: 145 · 2025: 143 · 2024: 67 · 2023: 21
FWCI
52.39
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • DR-NTU (Nanyang Technological University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Science and Technology (2022ZD0114805)
  • Fundamental Research Funds for the Central Universities (2024300373)
  • National Natural Science Foundation of China (62376118, 62006112, 62250069, 61921006)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Data Stream Mining Techniques
Keywords
class-incremental learning, catastrophic forgetting, continual learning, image classification, memory budget, vision transformer, convolutional neural networks

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review