Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning (2402.04129v1)

Published 6 Feb 2024 in cs.LG and cs.CV

Abstract: Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superior performance to prominent rehearsal-based ones. Rehearsal-free CIL methods struggle with distinguishing classes from different tasks, as those are not trained together. In this work we propose a regularization method based on virtual outliers to tighten decision boundaries of the classifier, such that confusion of classes among different tasks is mitigated. Recent prompt-based methods often require a pool of task-specific prompts, in order to prevent overwriting knowledge of previous tasks with that of the new task, leading to extra computation in querying and composing an appropriate prompt from the pool. This additional cost can be eliminated, without sacrificing accuracy, as we reveal in the paper. We illustrate that a simplified prompt-based method can achieve results comparable to previous state-of-the-art (SOTA) methods equipped with a prompt pool, using much less learnable parameters and lower inference cost. Our regularization method has demonstrated its compatibility with different prompt-based methods, boosting those previous SOTA rehearsal-free CIL methods' accuracy on the ImageNet-R and CIFAR-100 benchmarks. Our source code is available at https://github.com/jpmorganchase/ovor.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Conditional channel gated networks for task-aware continual learning. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 3930–3939. Computer Vision Foundation / IEEE, 2020. doi: 10.1109/CVPR42600.2020.00399. URL https://openaccess.thecvf.com/content_CVPR_2020/html/Abati_Conditional_Channel_Gated_Networks_for_Task-Aware_Continual_Learning_CVPR_2020_paper.html.
  2. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
  3. Dark experience for general continual learning: a strong, simple baseline. In Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020. URL https://proceedings.neurips.cc/paper/2020/hash/b704ea2c39778f07c617f6b7ce480e9e-Abstract.html.
  4. Co22{}^{\mbox{2}}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTl: Contrastive continual learning. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp.  9496–9505. IEEE, 2021. doi: 10.1109/ICCV48922.2021.00938. URL https://doi.org/10.1109/ICCV48922.2021.00938.
  5. CPR: classifier-projection regularization for continual learning. In Proceedings of the International Conference on Learning Representations, 2020.
  6. Continual learning with tiny episodic memories. CoRR, abs/1902.10486, 2019. URL http://arxiv.org/abs/1902.10486.
  7. Promptfusion: Decoupling stability and plasticity for continual learning. CoRR, abs/2303.07223, 2023. doi: 10.48550/arXiv.2303.07223. URL https://doi.org/10.48550/arXiv.2303.07223.
  8. Towards unknown-aware learning with virtual outlier synthesis. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=TW7d65uYu5M.
  9. Adversarial continual learning. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (eds.), Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XI, volume 12356 of Lecture Notes in Computer Science, pp.  386–402. Springer, 2020. doi: 10.1007/978-3-030-58621-8_23. URL https://doi.org/10.1007/978-3-030-58621-8_23.
  10. The many faces of robustness: A critical analysis of out-of-distribution generalization. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp.  8320–8329, 2021a. doi: 10.1109/ICCV48922.2021.00823.
  11. Natural adversarial examples. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pp.  15262–15271. Computer Vision Foundation / IEEE, 2021b. doi: 10.1109/CVPR46437.2021.01501. URL https://openaccess.thecvf.com/content/CVPR2021/html/Hendrycks_Natural_Adversarial_Examples_CVPR_2021_paper.html.
  12. Posterior meta-replay for continual learning. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (eds.), Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 14135–14149, 2021. URL https://proceedings.neurips.cc/paper/2021/hash/761b42cfff120aac30045f7a110d0256-Abstract.html.
  13. Lifelong learning via progressive distillation and retrospection. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
  14. Lora: Low-rank adaptation of large language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, 2022. URL https://openreview.net/forum?id=nZeVKeeFYf9.
  15. Peter J. Huber. Robust estimation of a location parameter. Annals of Mathematical Statistics, 35:492–518, 1964.
  16. Visual prompt tuning. In Shai Avidan, Gabriel J. Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (eds.), Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXIII, volume 13693 of Lecture Notes in Computer Science, pp.  709–727. Springer, 2022. doi: 10.1007/978-3-031-19827-4_41. URL https://doi.org/10.1007/978-3-031-19827-4_41.
  17. A theoretical study on solving continual learning. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (eds.), Advances in Neural Information Processing Systems, volume 35, pp.  5065–5079. Curran Associates, Inc., 2022. URL https://proceedings.neurips.cc/paper_files/paper/2022/file/20f44da80080d76bbc35bca0027f14e6-Paper-Conference.pdf.
  18. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun (eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015. URL http://arxiv.org/abs/1412.6980.
  19. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114:3521 – 3526, 2016.
  20. Similarity of neural network representations revisited. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp.  3519–3529. PMLR, 2019. URL http://proceedings.mlr.press/v97/kornblith19a.html.
  21. Learning multiple layers of features from tiny images.(2009), 2009.
  22. A continual learning survey: Defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell., 44(7):3366–3385, 2022. doi: 10.1109/TPAMI.2021.3057446. URL https://doi.org/10.1109/TPAMI.2021.3057446.
  23. The power of scale for parameter-efficient prompt tuning. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih (eds.), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pp.  3045–3059. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021.emnlp-main.243. URL https://doi.org/10.18653/v1/2021.emnlp-main.243.
  24. Prefix-tuning: Optimizing continuous prompts for generation. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp.  4582–4597. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021.acl-long.353. URL https://doi.org/10.18653/v1/2021.acl-long.353.
  25. Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12):2935–2947, 2018. doi: 10.1109/TPAMI.2017.2773081.
  26. Energy-based out-of-distribution detection. In Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020. URL https://proceedings.neurips.cc/paper/2020/hash/f5496252609c43eb8a3d147ab9b9c006-Abstract.html.
  27. Remind of the past: Incremental learning with analogical prompts. CoRR, abs/2303.13898, 2023. doi: 10.48550/arXiv.2303.13898. URL https://doi.org/10.48550/arXiv.2303.13898.
  28. Online continual learning in image classification: An empirical survey. Neurocomputing, 469:28–51, 2022. doi: 10.1016/j.neucom.2021.10.021. URL https://doi.org/10.1016/j.neucom.2021.10.021.
  29. Catastrophic interference in connectionist networks: The sequential learning problem. Psychology of Learning and Motivation, 24:109–165, 1989.
  30. RanPAC: Random projections and pre-trained models for continual learning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. URL https://openreview.net/forum?id=aec58UfBzA.
  31. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pp.  427–436. IEEE Computer Society, 2015. doi: 10.1109/CVPR.2015.7298640. URL https://doi.org/10.1109/CVPR.2015.7298640.
  32. Learning to remember: A synaptic plasticity driven framework for continual learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 11321–11329. Computer Vision Foundation / IEEE, 2019. doi: 10.1109/CVPR.2019.01158. URL http://openaccess.thecvf.com/content_CVPR_2019/html/Ostapenko_Learning_to_Remember_A_Synaptic_Plasticity_Driven_Framework_for_Continual_CVPR_2019_paper.html.
  33. Gdumb: A simple approach that questions our progress in continual learning. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (eds.), Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part II, volume 12347 of Lecture Notes in Computer Science, pp.  524–540. Springer, 2020. doi: 10.1007/978-3-030-58536-5_31. URL https://doi.org/10.1007/978-3-030-58536-5_31.
  34. itaml: An incremental task-agnostic meta-learning approach. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 13585–13594. Computer Vision Foundation / IEEE, 2020. doi: 10.1109/CVPR42600.2020.01360. URL https://openaccess.thecvf.com/content_CVPR_2020/html/Rajasegaran_iTAML_An_Incremental_Task-Agnostic_Meta-learning_Approach_CVPR_2020_paper.html.
  35. icarl: Incremental classifier and representation learning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp. 5533–5542. IEEE Computer Society, 2017. doi: 10.1109/CVPR.2017.587. URL https://doi.org/10.1109/CVPR.2017.587.
  36. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis., 115(3):211–252, 2015. doi: 10.1007/s11263-015-0816-y. URL https://doi.org/10.1007/s11263-015-0816-y.
  37. Progressive neural networks. CoRR, abs/1606.04671, 2016. URL http://arxiv.org/abs/1606.04671.
  38. Overcoming catastrophic forgetting with hard attention to the task. In Jennifer G. Dy and Andreas Krause (eds.), Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of Machine Learning Research, pp.  4555–4564. PMLR, 2018. URL http://proceedings.mlr.press/v80/serra18a.html.
  39. Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.  11909–11919, June 2023a.
  40. A closer look at rehearsal-free continual learning *. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.  2410–2420, 2023b. doi: 10.1109/CVPRW59228.2023.00239.
  41. How to train your vit? data, augmentation, and regularization in vision transformers. Trans. Mach. Learn. Res., 2022, 2022. URL https://openreview.net/forum?id=4nPswr1KcP.
  42. Non-parametric outlier synthesis. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=JHklpEZqduQ.
  43. Brain-inspired replay for continual learning with artificial neural networks. Nature Communications, 11, 2020.
  44. Continual learning with hypernetworks. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. URL https://openreview.net/forum?id=SJgwNerKvB.
  45. The caltech-ucsd birds-200-2011 dataset. Technical Report CNS-TR-2011-001, California Institute of Technology, 2011.
  46. S-prompts learning with pre-trained transformers: An occam’s razor for domain incremental learning. In NeurIPS, 2022a. URL http://papers.nips.cc/paper_files/paper/2022/hash/25886d7a7cf4e33fd44072a0cd81bf30-Abstract-Conference.html.
  47. Learn-prune-share for lifelong learning. In Claudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, and Xindong Wu (eds.), 20th IEEE International Conference on Data Mining, ICDM 2020, Sorrento, Italy, November 17-20, 2020, pp.  641–650. IEEE, 2020. doi: 10.1109/ICDM50108.2020.00073. URL https://doi.org/10.1109/ICDM50108.2020.00073.
  48. Dualprompt: Complementary prompting for rehearsal-free continual learning. In Shai Avidan, Gabriel Brostow, Moustapha Cissé, Giovanni Maria Farinella, and Tal Hassner (eds.), Computer Vision – ECCV 2022, pp. 631–648, Cham, 2022b. Springer Nature Switzerland.
  49. Learning to prompt for continual learning. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.  139–149, 2022c. doi: 10.1109/CVPR52688.2022.00024.
  50. Continual learning through synaptic intelligence. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, pp.  3987–3995. JMLR.org, 2017.
  51. Slca: Slow learner with classifier alignment for continual learning on a pre-trained model. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp.  19148–19158, October 2023.
  52. Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need. CoRR, abs/2303.07338, 2023. doi: 10.48550/arXiv.2303.07338. URL https://doi.org/10.48550/arXiv.2303.07338.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Wei-Cheng Huang (8 papers)
  2. Chun-Fu Chen (28 papers)
  3. Hsiang Hsu (24 papers)
Citations (5)
View on Semantic Scholar
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - jpmorganchase/ovor: GTAR OVOR Project (9 stars)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets