CoChat
Sign Up
Cited by 740Domain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsData Stream Mining Techniques

Class-Incremental Learning: Survey and Performance Evaluation on Image Classification

Open access
Masana, Marc, Liu, Xialei, Twardowski, Bartłomiej, Menta, Mikel, Bagdanov, Andrew D., van de Weijer, Joost·2023·IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/tpami.2022.3213473
Open this paper in CoChat — free accountOpen PDF

Abstract

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored - also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task-incremental learning, where a task-ID is provided at inference time. Recently, we have seen a shift towards class-incremental learning where the learner must discriminate at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing class-incremental learning methods for image classification, and in particular, we perform an extensive experimental evaluation on thirteen class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale image classification datasets, an investigation into small and large domain shifts, and a comparison of various network architectures.

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.2022.3213473

Cites

20 of 20 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: 103

  1. [2][2] S. Thrun, 'Is learning the n-th thing any easier than learning the first?' in Proc. Adv. Neural Information Processing Systems , 1996. -
  2. [4][4] I. J. Goodfellow, M. Mirza, D. Xiao, A. Courville, and Y. Bengio, 'An empirical investigation of catastrophic forgetting in gradient-based neural networks,' in Proc. International Conference on Learning Representations , 2014. -
  3. [8][8] G. M. van de Ven and A. S. Tolias, 'Three scenarios for continual learning,' in Proc. Adv. Neural Information Processing Systems Workshop on Continual Learning , 2018. -
  4. [11][11] R. Aljundi, P. Chakravarty, and T. Tuytelaars, 'Expert gate: Lifelong learning with a network of experts,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2017. -
  5. [12][12] A. Chaudhry, M. Ranzato, M. Rohrbach, and M. Elhoseiny, 'Efficient lifelong learning with a-gem,' in Proc. International Conference on Learning Representations , 2019. -
  6. [13][13] M. Delange, R. Aljundi, M. Masana, S. Parisot, X. Jia, A. Leonardis, G. Slabaugh, and T. Tuytelaars, 'A continual learning survey: Defying forgetting in classification tasks,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021. -
  7. [15][15] P. McClure, C. Y. Zheng, J. R. Kaczmarzyk, J. A. Lee, S. S. Ghosh, D. Nielson, P. Bandettini, and F. Pereira, 'Distributed weight consolidation: a brain segmentation case study,' in Proc. Adv. Neural Information Processing Systems , 2018. -
  8. [17][17] O. Sharir, B. Peleg, and Y. Shoham, 'The cost of training nlp models: A concise overview,' arXiv , 2020. -
  9. [18][18] D. Lopez-Paz and M. Ranzato, 'Gradient episodic memory for continual learning,' in Proc. Adv. Neural Information Processing Systems , 2017. -
  10. [19][19] Z. Mai, R. Li, J. Jeong, D. Quispe, H. Kim, and S. Sanner, 'Online continual learning in image classification: An empirical survey,' Neurocomputing , vol. 469, pp. 28-51, 2022. -
  11. [20][20] Z. Li and D. Hoiem, 'Learning without forgetting,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017. -
  12. [21][21] S. Hou, X. Pan, C. C. Loy, Z. Wang, and D. Lin, 'Learning a unified classifier incrementally via rebalancing,' in Proc. IEEE International Conference on Computer Vision , 2019. -
  13. [22][22] Y. Wu, Y. Chen, L. Wang, Y. Ye, Z. Liu, Y. Guo, and Y. Fu, 'Large scale incremental learning,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2019. -
  14. [23][23] F. M. Castro, M. J. Mar´ ın-Jim´ enez, N. Guil, C. Schmid, and K. Alahari, 'End-to-end incremental learning,' in Proc. European Conference on Computer Vision , 2018. -
  15. [25][25] J. Schwarz, J. Luketina, W. M. Czarnecki, A. Grabska-Barwinska, Y. W. Teh, R. Pascanu, and R. Hadsell, 'Progress & compress: A scalable framework for continual learning,' in Proc. International Conference on Machine Learning , 2018. -
  16. [26][26] A. A. Rusu, N. C. Rabinowitz, G. Desjardins, H. Soyer, J. Kirkpatrick, K. Kavukcuoglu, R. Pascanu, and R. Hadsell, 'Progressive neural networks,' arXiv , 2016. -
  17. [27][27] J. Rajasegaran, M. Hayat, S. Khan, F. S. Khan, and L. Shao, 'Random path selection for incremental learning,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  18. [28][28] T. L. Hayes, K. Kafle, R. Shrestha, M. Acharya, and C. Kanan, 'Remind your neural network to prevent catastrophic forgetting,' in Proc. European Conference on Computer Vision , 2020. -
  19. [29][29] A. Mallya and S. Lazebnik, 'Packnet: Adding multiple tasks to a single network by iterative pruning,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2018. -
  20. [30][30] H. Shin, J. K. Lee, J. Kim, and J. Kim, 'Continual learning with deep generative replay,' in Proc. Adv. Neural Information Processing Systems , 2017. -
  21. [31][31] C. V. Nguyen, Y. Li, T. D. Bui, and R. E. Turner, 'Variational continual learning,' in Proc. International Conference on Learning Representations , 2018. -
  22. [34][34] F. Zenke, B. Poole, and S. Ganguli, 'Continual learning through synaptic intelligence,' in Proc. International Conference on Machine Learning , 2017. -
  23. [35][35] H. Jung, J. Ju, M. Jung, and J. Kim, 'Less-forgetting learning in deep neural networks,' arXiv , 2016. -
  24. [36][36] C. Wu, L. Herranz, X. Liu, Y. Wang, J. van de Weijer, and B. Raducanu, 'Memory replay GANs: learning to generate images from new categories without forgetting,' in Proc. Adv. Neural Information Processing Systems , 2018. -
  25. [37][37] Y. Xiang, Y. Fu, P. Ji, and H. Huang, 'Incremental learning using conditional adversarial networks,' in Proc. IEEE International Conference on Computer Vision , 2019. -
  26. [38][38] S.-W. Lee, J.-H. Kim, J. Jun, J.-W. Ha, and B.-T. Zhang, 'Overcoming catastrophic forgetting by incremental moment matching,' in Proc. Adv. Neural Information Processing Systems , 2017. -
  27. [39][39] X. Liu, M. Masana, L. Herranz, J. Van de Weijer, A. M. Lopez, and A. D. Bagdanov, 'Rotate your networks: Better weight consolidation and less catastrophic forgetting,' in International Conference on Pattern Recognition , 2018. -
  28. [41][41] D. L. Silver and R. E. Mercer, 'The task rehearsal method of lifelong learning: Overcoming impoverished data,' in Conference of the Canadian Society for Computational Studies of Intelligence , 2002. -
  29. [42][42] J. Zhang, J. Zhang, S. Ghosh, D. Li, S. Tasci, L. Heck, H. Zhang, and C.-C. J. Kuo, 'Class-incremental learning via deep model consolidation,' in Proc. IEEE Winter Conference on Applications of Computer Vision , 2020. -
  30. [43][43] K. Lee, K. Lee, J. Shin, and H. Lee, 'Overcoming catastrophic forgetting with unlabeled data in the wild,' in Proc. IEEE International Conference on Computer Vision , 2019. -
  31. [44][44] J. Lee, H. G. Hong, D. Joo, and J. Kim, 'Continual learning with extended kronecker-factored approximate curvature,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2020. -
  32. [45][45] C. Buciluˇ a, R. Caruana, and A. Niculescu-Mizil, 'Model compression,' in International Conference on Knowledge Discovery and Data Mining , 2006. -
  33. [46][46] G. Hinton, O. Vinyals, and J. Dean, 'Distilling the knowledge in a neural network,' in Proc. Adv. Neural Information Processing Systems Workshop on Deep Learning , 2014. -
  34. [47][47] Y. Liu, A.-A. Liu, Y. Su, B. Schiele, and Q. Sun, 'Mnemonics training: Multi-class incremental learning without forgetting,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2020. -
  35. [48][48] S. Zagoruyko and N. Komodakis, 'Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer,' in Proc. International Conference on Learning Representations , 2017. -
  36. [49][49] P. Dhar, R. V. Singh, K.-C. Peng, Z. Wu, and R. Chellappa, 'Learning without memorizing,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2019. -
  37. [50][50] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, 'Grad-cam: Visual explanations from deep networks via gradient-based localization,' in Proc. IEEE International Conference on Computer Vision , 2017. -
  38. [51][51] S. Hou, X. Pan, C. C. Loy, Z. Wang, and D. Lin, 'Lifelong learning via progressive distillation and retrospection,' in Proc. European Conference on Computer Vision , 2018. -
  39. [52][52] K. Javed and F. Shafait, 'Revisiting distillation and incremental classifier learning,' in Asian Conference on Computer Vision , 2018. -
  40. [53][53] O. Ostapenko, M. Puscas, T. Klein, P. J¨ ahnichen, and M. Nabi, 'Learning to remember: A synaptic plasticity driven framework for continual learning,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2019. -
  41. [54][54] R. Kemker and C. Kanan, 'Fearnet: Brain-inspired model for incremental learning,' in Proc. International Conference on Learning Representations , 2018. -
  42. [55][55] M. Welling, 'Herding dynamical weights to learn,' in Proc. International Conference on Machine Learning , 2009. -
  43. [56][56] A. Prabhu, P. H. Torr, and P. K. Dokania, 'Gdumb: A simple approach that questions our progress in continual learning,' in Proc. European Conference on Computer Vision . Springer, 2020, pp. 524-540. -
  44. [57][57] M. K. Titsias, J. Schwarz, A. G. d. G. Matthews, R. Pascanu, and Y. W. Teh, 'Functional regularisation for continual learning with gaussian processes,' in Proc. International Conference on Learning Representations , 2020. -
  45. [58][58] P. Pan, S. Swaroop, A. Immer, R. Eschenhagen, R. E. Turner, and M. E. Khan, 'Continual deep learning by functional regularisation of memorable past,' in Proc. Adv. Neural Information Processing Systems , 2020. -
  46. [59][59] R. Ratcliff, 'Connectionist models of recognition memory: constraints imposed by learning and forgetting functions.' Psychological review , 1990. -
  47. [61][61] G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, 'Continual lifelong learning with neural networks: A review,' Neural Networks , 2019. -
  48. [62][62] B. Pf¨ ulb and A. Gepperth, 'A comprehensive, applicationoriented study of catastrophic forgetting in dnns,' in Proc. International Conference on Learning Representations , 2019. -
  49. [64][64] M. Masana, T. Tuytelaars, and J. van de Weijer, 'Ternary feature masks: continual learning without any forgetting,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops , 2021. -
  50. [65][65] A. Mallya, D. Davis, and S. Lazebnik, 'Piggyback: Adapting a single network to multiple tasks by learning to mask weights,' in Proc. European Conference on Computer Vision , 2018. -
  51. [66][66] J. Serra, D. Suris, M. Miron, and A. Karatzoglou, 'Overcoming catastrophic forgetting with hard attention to the task,' in Proc. International Conference on Machine Learning , 2018. -
  52. [67][67] A. Rosenfeld and J. K. Tsotsos, 'Incremental learning through deep adaptation,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018. -
  53. [68][68] C. Fernando, D. Banarse, C. Blundell, Y. Zwols, D. Ha, A. A. Rusu, A. Pritzel, and D. Wierstra, 'Pathnet: Evolution channels gradient descent in super neural networks,' arXiv , 2017. -
  54. [69][69] T. Xiao, J. Zhang, K. Yang, Y. Peng, and Z. Zhang, 'Error-driven incremental learning in deep convolutional neural network for large-scale image classification,' in ACM International Conference on Multimedia , 2014. -
  55. [70][70] S. Ebrahimi, F. Meier, R. Calandra, T. Darrell, and M. Rohrbach, 'Adversarial continual learning,' in Proc. European Conference on Computer Vision , 2020. -
  56. [71][71] A. Chaudhry, M. Rohrbach, M. Elhoseiny, T. Ajanthan, P. K. Dokania, P. H. Torr, and M. Ranzato, 'Continual learning with tiny episodic memories,' in Proc. International Conference on Machine Learning , 2019. -
  57. [73][73] D. Rolnick, A. Ahuja, J. Schwarz, T. P. Lillicrap, and G. Wayne, 'Experience replay for continual learning,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  58. [74][74] R. Aljundi, M. Lin, B. Goujaud, and Y. Bengio, 'Gradient based sample selection for online continual learning,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  59. [75][75] R. Aljundi, E. Belilovsky, T. Tuytelaars, L. Charlin, M. Caccia, M. Lin, and L. Page-Caccia, 'Online continual learning with maximal interfered retrieval,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  60. [76][76] M. Riemer, T. Klinger, D. Bouneffouf, and M. Franceschini, 'Scalable recollections for continual lifelong learning,' in Proc. AAAI Conference Artificial Intelligence , 2019. -
  61. [77][77] M. Riemer, I. Cases, R. Ajemian, M. Liu, I. Rish, Y. Tu, and G. Tesauro, 'Learning to learn without forgetting by maximizing transfer and minimizing interference,' in Proc. International Conference on Learning Representations , 2019. -
  62. [78][78] A. Nichol, J. Achiam, and J. Schulman, 'On first-order metalearning algorithms,' arXiv , 2018. -
  63. [79][79] S. Farquhar and Y. Gal, 'A unifying bayesian view of continual learning,' in Proc. Adv. Neural Information Processing Systems Workshop on Deep Learning , 2019. -
  64. [80][80] H. Ahn, S. Cha, D. Lee, and T. Moon, 'Uncertainty-based continual learning with adaptive regularization,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  65. [81][81] Y. Chen, T. Diethe, and N. Lawrence, 'Facilitating bayesian continual learning by natural gradients and stein gradients,' in Proc. Adv. Neural Information Processing Systems Workshop on Continual Learning , 2018. -
  66. [82][82] S. Swaroop, C. V. Nguyen, T. D. Bui, and R. E. Turner, 'Improving and understanding variational continual learning,' in Proc. Adv. Neural Information Processing Systems Workshop on Continual Learning , 2018. -
  67. [83][83] T. Adel, H. Zhao, and R. E. Turner, 'Continual learning with adaptive weights (claw),' in Proc. International Conference on Learning Representations , 2020. -
  68. [84][84] S. Ebrahimi, M. Elhoseiny, T. Darrell, and M. Rohrbach, 'Uncertainty-guided continual learning with bayesian neural networks,' in Proc. International Conference on Learning Representations , 2020. -
  69. [85][85] C. Zeno, I. Golan, E. Hoffer, and D. Soudry, 'Task agnostic continual learning using online variational bayes,' in Proc. Adv. Neural Information Processing Systems Workshop on Bayesian Deep Learning , 2018. -
  70. [86][86] M. Zhai, L. Chen, F. Tung, J. He, M. Nawhal, and G. Mori, 'Lifelong gan: Continual learning for conditional image generation,' in Proc. IEEE International Conference on Computer Vision , 2019. -
  71. [88][88] R. Girshick, 'Fast r-cnn,' in IEEE International Conference on Computer Vision , 2015. -
  72. [89][89] Y. Hao, Y. Fu, Y.-G. Jiang, and Q. Tian, 'An end-to-end architecture for class-incremental object detection with knowledge distillation,' in International Conference on Multimedia and Expo , 2019. -
  73. [91][91] U. Michieli and P. Zanuttigh, 'Incremental learning techniques for semantic segmentation,' in Proc. IEEE International Conference on Computer Vision Workshops , 2019. -
  74. [92][92] F. Cermelli, M. Mancini, S. R. Bulo, E. Ricci, and B. Caputo, 'Modeling the background for incremental learning in semantic segmentation,' in IEEE Conference on Computer Vision and Pattern Recognition , 2020. -
  75. [93][93] O. Tasar, Y. Tarabalka, and P. Alliez, 'Incremental learning for semantic segmentation of large-scale remote sensing data,' IEEE Applied Earth Observations and Remote Sensing , 2019. -
  76. [94][94] F. Ozdemir, P. Fuernstahl, and O. Goksel, 'Learn the new, keep the old: Extending pretrained models with new anatomy and images,' in International Conference on Medical Image Computing and Computer-Assisted Intervention , 2018. -
  77. [95][95] M. Schak and A. Gepperth, 'A study on catastrophic forgetting in deep lstm networks,' in International Conference on Artificial Neural Networks , 2019. -
  78. [96][96] R. Coop and I. Arel, 'Mitigation of catastrophic forgetting in recurrent neural networks using a fixed expansion layer,' in International Joint Conference on Neural Networks , 2013. -
  79. [97][97] T. Chen, I. Goodfellow, and J. Shlens, 'Net2net: Accelerating learning via knowledge transfer,' in Proc. International Conference on Learning Representations , 2016. -
  80. [99][99] R. Del Chiaro, B. Twardowski, A. D. Bagdanov, and J. Van de Weijer, 'Ratt: Recurrent attention to transient tasks for continual image captioning,' in International Conference on Machine Learning Workshop LifelongML , 2020. -
  81. [103][103] A. Quattoni and A. Torralba, 'Recognizing indoor scenes,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2009. -
  82. [105][105] J. Krause, M. Stark, J. Deng, and L. Fei-Fei, '3d object representations for fine-grained categorization,' in Proc. IEEE International Conference on Computer Vision Workshops , 2013. -
  83. [106][106] S. Maji, J. Kannala, E. Rahtu, M. Blaschko, and A. Vedaldi, 'Finegrained visual classification of aircraft,' eprint arXiv:1306.5151, Tech. Rep., 2013. - · arXiv
  84. [107][107] B. Yao, X. Jiang, A. Khosla, A. L. Lin, L. Guibas, and L. Fei-Fei, 'Human action recognition by learning bases of action attributes and parts,' in Proc. IEEE International Conference on Computer Vision , 2011. -
  85. [111][111] K. Simonyan and A. Zisserman, 'Very deep convolutional networks for large-scale image recognition,' in Proc. International Conference on Learning Representations , 2015. -
  86. [112][112] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, 'Going deeper with convolutions,' in IEEE Conference on Computer Vision and Pattern Recognition , 2015. -
  87. [113][113] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, 'Mobilenetv2: Inverted residuals and linear bottlenecks,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2018. -
  88. [114][114] A. Chaudhry, A. Gordo, P. K. Dokania, P. Torr, and D. LopezPaz, 'Using hindsight to anchor past knowledge in continual learning,' in Proc. AAAI Conference Artificial Intelligence , 2021. -
  89. [115][115] X. Liu, C. Wu, M. Menta, L. Herranz, B. Raducanu, A. D. Bagdanov, S. Jui, and J. van de Weijer, 'Generative feature replay for class-incremental learning,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops , 2020. -
  90. [116][116] A. Iscen, J. Zhang, S. Lazebnik, and C. Schmid, 'Memory-efficient incremental learning through feature adaptation,' in Proc. European Conference on Computer Vision , 2020. -
  91. [117][117] D. Rao, F. Visin, A. Rusu, R. Pascanu, Y. W. Teh, and R. Hadsell, 'Continual unsupervised representation learning,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  92. [118][118] L. Jing and Y. Tian, 'Self-supervised visual feature learning with deep neural networks: A survey,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020. -
  93. [119][119] L. Yu, B. Twardowski, X. Liu, L. Herranz, K. Wang, Y. Cheng, S. Jui, and J. v. d. Weijer, 'Semantic drift compensation for classincremental learning,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2020. -
  94. [120][120] S. Li, Y. Du, G. M. van de Ven, A. Torralba, and I. Mordatch, 'Energy-based models for continual learning,' in Proc. International Conference on Learning Representations , 2021. -
  95. [121][121] J. Schmidhuber, 'Evolutionary principles in self-referential learning,' Diploma thesis, Tech. Univ. Munich , 1987. -
  96. [122][122] K. Javed and M. White, 'Meta-learning representations for continual learning,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  97. [123][123] R. Aljundi, K. Kelchtermans, and T. Tuytelaars, 'Task-free continual learning,' in IEEE Conference on Computer Vision and Pattern Recognition , 2019. -
  98. [124][124] J. Rajasegaran, S. Khan, M. Hayat, F. S. Khan, and M. Shah, 'iTAML: An incremental task-agnostic meta-learning approach,' in Proc. IEEE Conference on Computer Vision and Pattern Recognition , 2020. -
  99. [125][125] M. De Lange and T. Tuytelaars, 'Continual prototype evolution: Learning online from non-stationary data streams,' in Proc. IEEE International Conference on Computer Vision , 2020. -
  100. [126][126] F. Kunstner, L. Balles, and P. Hennig, 'Limitations of the empirical fisher approximation for natural gradient descent,' in Proc. Adv. Neural Information Processing Systems , 2019. -
  101. [127][127] A. Torralba, R. Fergus, and W. T. Freeman, '80 million tiny images: A large data set for nonparametric object and scene recognition,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2008. -
  102. [130][130] M. Masana, B. Twardowski, and J. Van de Weijer, 'On class orderings for incremental learning,' in International Conference on Machine Learning Workshop on Continual Learning , 2020. -
  103. [132][132] S. Zagoruyko and N. Komodakis, 'Wide residual networks,' in Proc. British Machine Vision Conference , 2016. Marc Masana obtained his Ph.D. in computer vision at the Computer Vision Center from Universitat Aut` onoma de Barcelona, Spain in 2020 and is currently holding a post-doc position at TU Graz, Austria. His research interests concern machine learning, network compression, continual learning and novelty detection. Xialei Liu is currently an associate professor at Nankai University, China. Before that, he was a post-doc research associate at University of Edinburgh, UK. He obtained his PhD in 2020 from Universitat Aut` onoma de Barcelona, Spain. His research interests include lifelong learning, self-supervised learning, few-shot learning and long-tailed learning. Bartłomiej Twardowski obtained his Ph.D. in computer science from Warsaw University of Technology in 2018. Currently holding a post-doc position in Computer Vision Center, Universitat Aut` onoma de Barcelona. Mikel Menta obtained his M.Sc. in Computer Vision from Universitat Aut` onoma de Barcelona in 2018. Currently working as an applied researcher for Wide Eyes Technologies. Andrew D. Bagdanov Andrew D. Bagdanov is Associate Professor at the University of Florence, Italy. He received the Ph.D. from the University of Amsterdam in 2004, after which he was a postdoc at the University of Florence and the Universitat Aut` onoma de Barcelona, and was a Ramon y Cajal Fellow at the Computer Vision Center, Barcelona. His research spans a broad spectrum of computer vision, image processing and machine learning. Joost van de Weijer Joost van de Weijer received the Ph.D. degree from the University of Amsterdam in 2005. He was a Marie Curie IntraEuropean Fellow at INRIA Rhone-Alpes, France, and from 2008 to 2012 was a Ramon y Cajal Fellow at the Universitat Aut` onoma de Barcelona, Spain, where he is currently a Senior Scientist at the Computer Vision Center and leader of the LAMP Team.

Cited by

Sorted by citations

Authors
Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A. D., & van de Weijer, J.
Affiliations
Computer Vision Center (ES)
ORCID
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2023-05-01
Volume
45
Issue
5
Pages
5513-5533
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
DOI
10.1109/tpami.2022.3213473
OpenAlex
W3163939464
Cited by
740
References
20
Citations by year
2026: 119 · 2025: 215 · 2024: 223 · 2023: 135 · 2022: 32 · 2021: 16
FWCI
49.77
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Florence Research (University of Florence) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Huawei Kirin Solution
  • Generalitat de Catalunya (2019-FI_B2-00189)
  • Spanish Project (PID2019-104174GB-I00/AEI/10.13039/501100011033)
  • European Commission (951911 - AI4Media)
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, image classification, deep neural network, continual learning, domain shift, network architecture comparison, memory-efficient learning

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