Papers
Topics
Authors
Recent
Search
2000 character limit reached

TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning

Published 7 Dec 2023 in cs.CV | (2312.04225v1)

Abstract: Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. TLCE minimizes interference between old and new classes by mapping old class images to quasi-orthogonal prototypes using episodic training. It then ensembles diverse pre-trained models to better adapt to novel classes despite data imbalance. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Constrained few-shot class-incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2022, pp. 9057–9067.
  2. Self-promoted prototype refinement for few-shot class-incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2021, pp. 6801–6810.
  3. Few-shot incremental learning with continually evolved classifiers, in: IEEE Conf. Comput. Vis. Pattern Recog., 2021, pp. 12455–12464.
  4. Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima, Adv. Neural Inform. Process. Syst. 34 (2021) 6747–6761.
  5. A closer look at few-shot classification, in: Int. Conf. Learn. Represent., 2019.
  6. Rethinking few-shot image classification: a good embedding is all you need?, in: Eur. Conf. Comput. Vis., Springer, 2020, pp. 266–282.
  7. Imagenet large scale visual recognition challenge, Int. J. Comput. Vis. 115 (2015) 211–252.
  8. Learning multiple layers of features from tiny images (2009).
  9. Meta-learning in neural networks: A survey, IEEE Trans. Pattern Anal. Mach. Intell. 44 (2021) 5149–5169.
  10. Model-agnostic meta-learning for fast adaptation of deep networks, in: Int. Conf. Mach. Learn., PMLR, 2017, pp. 1126–1135.
  11. M. A. Jamal, G.-J. Qi, Task agnostic meta-learning for few-shot learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2019.
  12. Meta-learning with latent embedding optimization, in: Int. Conf. Learn. Represent., 2019.
  13. Siamese neural networks for one-shot image recognition, in: ICML deep learning workshop, 2015.
  14. Matching networks for one shot learning, Adv. Neural Inform. Process. Syst. 29 (2016).
  15. Prototypical networks for few-shot learning, Adv. Neural Inform. Process. Syst. 30 (2017).
  16. Learning to compare: Relation network for few-shot learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2018, pp. 1199–1208.
  17. Free lunch for few-shot learning: Distribution calibration, in: Int. Conf. Learn. Represent., 2021.
  18. Learning calibrated class centers for few-shot classification by pair-wise similarity, IEEE Trans. Image Process. 31 (2022) 4543–4555.
  19. Alleviating the sample selection bias in few-shot learning by removing projection to the centroid, in: Adv. Neural Inform. Process. Syst., 2022.
  20. P3dc-shot: Prior-driven discrete data calibration for nearest-neighbor few-shot classification, Image and Vision Computing (2023) 104736.
  21. Memory-efficient incremental learning through feature adaptation, in: Eur. Conf. Comput. Vis., Springer, 2020, pp. 699–715.
  22. Prototype augmentation and self-supervision for incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2021, pp. 5871–5880.
  23. Fetril: Feature translation for exemplar-free class-incremental learning, in: IEEE Winter Conf. Appl. Comput. Vis., 2023, pp. 3911–3920.
  24. Overcoming catastrophic forgetting in neural networks, Proc. Natl. Acad. Sci. 114 (2017) 3521–3526.
  25. Riemannian walk for incremental learning: Understanding forgetting and intransigence, in: Eur. Conf. Comput. Vis., 2018, pp. 532–547.
  26. Continual learning with extended kronecker-factored approximate curvature, in: IEEE Conf. Comput. Vis. Pattern Recog., 2020, pp. 9001–9010.
  27. icarl: Incremental classifier and representation learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2017, pp. 2001–2010.
  28. End-to-end incremental learning, in: Eur. Conf. Comput. Vis., 2018.
  29. R-dfcil: Relation-guided representation learning for data-free class incremental learning, in: Eur. Conf. Comput. Vis., Springer, 2022, pp. 423–439.
  30. Semantic drift compensation for class-incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2020, pp. 6982–6991.
  31. Adaptive aggregation networks for class-incremental learning, in: Eur. Conf. Comput. Vis., 2021, pp. 2544–2553.
  32. Few-shot class-incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2020, pp. 12180–12189. doi:10.1109/CVPR42600.2020.01220.
  33. Semantic-aware knowledge distillation for few-shot class-incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2021, pp. 2534–2543.
  34. Few-shot class-incremental learning via relation knowledge distillation, in: AAAI, volume 35, 2021, pp. 1255–1263.
  35. Forward compatible few-shot class-incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2022, pp. 9046–9056.
  36. Few-shot class-incremental learning from an open-set perspective, in: Eur. Conf. Comput. Vis., Springer, 2022, pp. 382–397.
  37. Learning with fantasy: Semantic-aware virtual contrastive constraint for few-shot class-incremental learning, IEEE Conf. Comput. Vis. Pattern Recog. (2023).
  38. Warping the space: Weight space rotation for class-incremental few-shot learning, in: Int. Conf. Learn. Represent., 2023.
  39. Few-shot lifelong learning, in: AAAI, volume 35, 2021, pp. 2337–2345.
  40. Metafscil: a meta-learning approach for few-shot class incremental learning, in: IEEE Conf. Comput. Vis. Pattern Recog., 2022, pp. 14166–14175.
  41. Memorizing complementation network for few-shot class-incremental learning, IEEE Trans. Image Process. (2023).
  42. Flexible few-shot class-incremental learning with prototype container, Neural. Comput. Appl. 35 (2023) 10875–10889.
  43. Robust high-dimensional memory-augmented neural networks, Nat. Commun. 12 (2021) 2468.
  44. Continual learning in deep networks: an analysis of the last layer, arXiv preprint arXiv:2106.01834 (2021).
  45. Simpleshot: Revisiting nearest-neighbor classification for few-shot learning, arXiv preprint arXiv:1911.04623 (2019).
  46. Learning a unified classifier incrementally via rebalancing, in: IEEE Conf. Comput. Vis. Pattern Recog., 2019, pp. 831–839.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Authors (3)

  1. Shuangmei Wang 
  2. Yang Cao 
  3. Tieru Wu 

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up