Papers
Topics
Authors
Recent
Search
2000 character limit reached

OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning

Published 5 Oct 2023 in cs.CV and cs.LG | (2310.03848v1)

Abstract: In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions. Such misclassifications can degrade model performance. Techniques like open set recognition offer a means to detect these novel samples, representing a significant area in the machine learning domain. In this paper, we introduce a deep class-incremental learning framework integrated with open set recognition. Our approach refines class-incrementally learned features to adapt them for distance-based open set recognition. Experimental results validate that our method outperforms state-of-the-art incremental learning techniques and exhibits superior performance in open set recognition compared to baseline methods.

Authors (3)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Task-free continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19), pages 11254–11263, Long Beach, USA, Jun. 2019.
  2. Towards open set deep networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), pages 1563–1572, Las Vegas, USA, Jun. 2016.
  3. Class-incremental continual learning into the extended der-verse. arXiv preprint arXiv:2201.00766, 2022.
  4. Dark experience for general continual learning: a strong, simple baseline. In Larochelle, H.; Ranzato, M.; Hadsell, R.; Balcan, M.F.; Lin, H., editors, Advances in Neural Information Processing Systems (NIPS’20), pages 15920–15930, Virtual, Dec 2020.
  5. Open-set recognition with gaussian mixture variational autoencoders. In Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI’21), Virtual, Feb. 2021.
  6. End-to-end incremental learning. In Proceedings of the European Conference on Computer Vision (ECCV’18), pages 233–248, Munich,Germany, Sep, 2018.
  7. Co2l: Contrastive continual learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR’21), pages 9516–9525, Virtual, Jun. 2021.
  8. Adversarial reciprocal points learning for open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11):8065–8081, 2022.
  9. Cohen, A. Numerical analysis of wavelet methods. Elsevier, 2003.
  10. Reducing network agnostophobia. In Thirty-second Annual Conference on Neural Information Processing Systems (NIPS’18), Montréal, Cananda, Dec 2018.
  11. Deep learning for aspect-based sentiment analysis: a comparative review. Expert systems with applications, 118:272–299, 2019.
  12. Generative openmax for multi-class open set classification. In 28th British Machine Vision Conference (BMVC’17), London, UK, Sep. 2017.
  13. Learning a neural-network-based representation for open set recognition. In Proceedings of the 2020 SIAM International Conference on Data Mining (ICDM’20), pages 154–162, Sorrento, Italy, Nov 2020.
  14. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, Las Vegas, US, Jun. 2016.
  15. Deep anomaly detection with outlier exposure. Proceedings of the International Conference on Learning Representations (ICLR’19), May 2019.
  16. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
  17. Learning a unified classifier incrementally via rebalancing. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19), Long Bench, US, Jun. 2019.
  18. Mmf: A loss extension for feature learning in open set recognition. In In Proceeding 30th International Conference on Artificial Neural Networks (ICANN’21), pages 319–331, Bratislava, Slovak, Sep 2021.
  19. Gradient-based editing of memory examples for online task-free continual learning. Advances in Neural Information Processing Systems (NIPS’21), pages 29193–29205, Dec 2021.
  20. Towards open world object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’21), Virtual, Jun, 2021.
  21. Supervised contrastive learning. arXiv preprint arXiv:2004.11362, 2020.
  22. Paraphrasing complex network: Network compression via factor transfer. arXiv preprint arXiv:1802.04977, 2018.
  23. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521–3526, 2017.
  24. Cifar-100 (canadian institute for advanced research).
  25. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, 40(12):2935–2947, 2017.
  26. Class anchor clustering: A loss for distance-based open set recognition. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV’21), pages 3570–3578, Virtual, Jan. 2021.
  27. Narkhede, S. Understanding auc-roc curve. Towards Data Science, 26(1):220–227, 2018.
  28. Relational knowledge distillation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19), pages 3967–3976, Long Beach, USA, Jun. 2019.
  29. Alp-kd: Attention-based layer projection for knowledge distillation. arXiv preprint arXiv:2012.14022, 2020.
  30. Generative-discriminative feature representations for open-set recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20), pages 11814–11823, Virtual, Jun. 2020.
  31. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR’17), pages 2001–2010, Hawaii, Jun. 2017.
  32. Experience replay for continual learning. In Advances in Neural Information Processing Systems (NIPS’19), Vancouver, Canada, Dec 2019.
  33. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550, 2014.
  34. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 115(3):211–252, 2015.
  35. Openmatch: Open-set consistency regularization for semi-supervised learning with outliers. ArXiv, abs/2105.14148, 2021.
  36. M2iosr: Maximal mutual information open set recognition. arXiv preprint arXiv:2108.02373, 2021.
  37. Open set recognition with conditional probabilistic generative models. arXiv preprint arXiv:2008.05129, 2020.
  38. Contrastive representation distillation. arXiv preprint arXiv:1910.10699, 2019.
  39. Similarity-preserving knowledge distillation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR’19), pages 1365–1374, Long Bench, US, Jun. 2019.
  40. Large scale incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19), pages 374–382, Long Bench, US, Jun. 2019.
  41. Convolutional prototype network for open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(5):2358–2370, 2020.
  42. Task-free continual learning via online discrepancy distance learning. Advances in Neural Information Processing Systems (NIPS’22), pages 23675–23688, Dec. 2022.
  43. Classification-reconstruction learning for open-set recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19), pages 4016–4025, Long Bench, US, Jun. 2019.
  44. Open-category classification by adversarial sample generation. In 26th International Joint Conference on Artificial Intelligence (IJCAI’17), Melbourne, Australia, Aug. 2017.
  45. Continual learning through synaptic intelligence. In Proceedings of the International Conference on Machine Learning (ICML’17), pages 3987–3995, Sydney, Australia, Aug 2017.
  46. Unleashing the power of contrastive self-supervised visual models via contrast-regularized fine-tuning. In Proceedings of the Advances in Neural Information Processing Systems (NIPS’21), pages 29848–29860, Virtual, Dec. 2021.
  47. Maintaining discrimination and fairness in class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20), pages 13208–13217, Virtual, Jun. 2020.
  48. Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 30(11):3212–3232, 2019.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

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

Sign Up to Generate

Open Problems

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

Generate Now

Continue Learning

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

Generate Now

Collections

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

Sign Up