mlsanityData to 7 Oct 2026

Knowledge Restore and Transfer for Multi-label Class-Incremental Learning

arXiv 2302.13334 ↗First posted 26 Feb 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although there have been many anti-forgetting methods to solve the problem of catastrophic forgetting in class-incremental learning, these methods have difficulty in solving the MLCIL problem due to label absence and information dilution. In this paper, we propose a knowledge restore and transfer (KRT) framework for MLCIL, which includes a dynamic pseudo-label (DPL) module to restore the old class knowledge and an incremental cross-attention(ICA) module to save session-specific knowledge and transfer old class knowledge to the new model sufficiently. Besides, we propose a token loss to jointly optimize the incremental cross-attention module. Experimental results on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on multi-label class-incremental learning tasks.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 65 of its 81 references that are in the map. First posted on arXiv 26 Feb 2023.

Builds on

65 of 81 references.

References · 65

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  7. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2020Knowledge Distillation: A Surveycited by 1,578
  10. 2016Progressive Neural Networkscited by 1,332
  11. 2017Continual Learning with Deep Generative Replaycited by 1,152
  12. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
38 more
  1. 2018Experience Replay for Continual Learningcited by 1,074
  2. 2021Learning to Prompt for Continual Learningcited by 938
  3. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  4. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  5. 2021Going deeper with Image Transformerscited by 759
  6. 2017Focal Loss for Dense Object Detectioncited by 749
  7. 2019Large Scale Incremental Learningcited by 727
  8. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  9. 2018End-to-End Incremental Learningcited by 596
  10. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  11. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  12. 2020Asymmetric Loss For Multi-Label Classificationcited by 379
  13. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  14. 2021Towards Open World Object Detectioncited by 297
  15. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  16. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 281
  17. 2018Learning without Memorizingcited by 249
  18. 2020Few-Shot Class-Incremental Learningcited by 249
  19. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  20. 2021Co2L: Contrastive Continual Learningcited by 243
  21. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  22. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  23. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  24. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 189
  25. 2020PLOP: Learning without Forgetting for Continual Semantic Segmentationcited by 177
  26. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  27. 2020General Multi-label Image Classification with Transformerscited by 126
  28. 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 126
  29. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  30. 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
  31. 2020Conditional Channel Gated Networks for Task-Aware Continual Learningcited by 115
  32. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 114
  33. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  34. 2019Overcoming Catastrophic Forgetting with Unlabeled Data in the Wildcited by 111
  35. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  36. 2017Multi-label Image Recognition by Recurrently Discovering Attentional Regionscited by 83
  37. 2021RECALL: Replay-based Continual Learning in Semantic Segmentationcited by 83
  38. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 80

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 2.

7 papers.

  1. 2024Confidence Self-Calibration for Multi-Label Class-Incremental Learningcited by 6
  2. 2024Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaborationcited by 4
  3. 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learningcited by 3
  4. 2025Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learningcited by 1
  5. 2024Multi-label Class Incremental Emotion Decoding with Augmented Emotional Semantics Learningcited by 0
  6. 2026P2L-CA: An Effective Parameter Tuning Framework for Rehearsal-Free Multi-Label Class-Incremental Learningcited by 0
  7. 2026Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learningcited by 0