Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Active Generalized Category Discovery (2403.04272v1)

Published 7 Mar 2024 in cs.CV

Abstract: Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes. Given that knowledge learned from old classes is not fully transferable to new classes, and that novel categories are fully unlabeled, GCD inherently faces intractable problems, including imbalanced classification performance and inconsistent confidence between old and new classes, especially in the low-labeling regime. Hence, some annotations of new classes are deemed necessary. However, labeling new classes is extremely costly. To address this issue, we take the spirit of active learning and propose a new setting called Active Generalized Category Discovery (AGCD). The goal is to improve the performance of GCD by actively selecting a limited amount of valuable samples for labeling from the oracle. To solve this problem, we devise an adaptive sampling strategy, which jointly considers novelty, informativeness and diversity to adaptively select novel samples with proper uncertainty. However, owing to the varied orderings of label indices caused by the clustering of novel classes, the queried labels are not directly applicable to subsequent training. To overcome this issue, we further propose a stable label mapping algorithm that transforms ground truth labels to the label space of the classifier, thereby ensuring consistent training across different active selection stages. Our method achieves state-of-the-art performance on both generic and fine-grained datasets. Our code is available at https://github.com/mashijie1028/ActiveGCD

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Contextual diversity for active learning. In European Conference on Computer Vision, pages 137–153, 2020.
  2. Pseudo-labeling and confirmation bias in deep semi-supervised learning. In 2020 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2020.
  3. Deep batch active learning by diverse, uncertain gradient lower bounds. In International Conference on Learning Representations, 2020.
  4. Towards distribution-agnostic generalized category discovery. In Advances in Neural Information Processing Systems, pages 58625–58647, 2023.
  5. Open-world semi-supervised learning. In International Conference on Learning Representations, 2022.
  6. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, 33:9912–9924, 2020.
  7. Emerging properties in self-supervised vision transformers. In Proceedings of the International Conference on Computer Vision (ICCV), 2021.
  8. Human active learning. Advances in neural information processing systems, 21, 2008.
  9. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  10. Parametric information maximization for generalized category discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1729–1739, 2023.
  11. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  12. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations, 2021.
  13. Contrastive active learning under class distribution mismatch. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4260–4273, 2022.
  14. Xcon: Learning with experts for fine-grained category discovery. In British Machine Vision Conference (BMVC), 2022.
  15. A unified objective for novel class discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9284–9292, 2021.
  16. Recent advances in open set recognition: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10):3614–3631, 2021.
  17. Class-relation knowledge distillation for novel class discovery. lamp, 12(15.0):17–5, 2023.
  18. On calibration of modern neural networks. In International conference on machine learning, pages 1321–1330. PMLR, 2017.
  19. Dual mean-teacher: An unbiased semi-supervised framework for audio-visual source localization. In Advances in Neural Information Processing Systems, pages 48639–48661, 2023.
  20. Learning to discover novel visual categories via deep transfer clustering. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8401–8409, 2019.
  21. Automatically discovering and learning new visual categories with ranking statistics. In International Conference on Learning Representations, 2020.
  22. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International Conference on Learning Representations, 2017.
  23. Active learning by learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 2015.
  24. Active learning by querying informative and representative examples. Advances in neural information processing systems, 23, 2010.
  25. Supervised contrastive learning. Advances in neural information processing systems, 33:18661–18673, 2020.
  26. 3d object representations for fine-grained categorization. In Proceedings of the IEEE international conference on computer vision workshops, pages 554–561, 2013.
  27. Learning multiple layers of features from tiny images. 2009.
  28. Harold W Kuhn. The hungarian method for the assignment problem. Naval research logistics quarterly, 2(1-2):83–97, 1955.
  29. Prototypical contrastive learning of unsupervised representations. In International Conference on Learning Representations, 2021.
  30. Towards trustworthy dataset distillation. arXiv preprint arXiv:2307.09165, 2023.
  31. Cathlin Macaulay. Transfer of learning. In Transfer of learning in professional and vocational education, pages 17–22. Routledge, 2002.
  32. James MacQueen et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, pages 281–297. Oakland, CA, USA, 1967.
  33. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151, 2013.
  34. Active learning for open-set annotation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 41–49, 2022.
  35. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2009.
  36. Meta-query-net: Resolving purity-informativeness dilemma in open-set active learning. Advances in Neural Information Processing Systems, 35:31416–31429, 2022.
  37. Active learning by feature mixing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12237–12246, 2022.
  38. Dynamic conceptional contrastive learning for generalized category discovery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7579–7588, 2023.
  39. A survey of deep active learning. ACM computing surveys (CSUR), 54(9):1–40, 2021.
  40. Margin-based active learning for structured output spaces. In Machine Learning: ECML 2006: 17th European Conference on Machine Learning Berlin, Germany, September 18-22, 2006 Proceedings 17, pages 413–424. Springer, 2006.
  41. Active hidden markov models for information extraction. In International symposium on intelligent data analysis, pages 309–318. Springer, 2001.
  42. Active learning for convolutional neural networks: A core-set approach. In International Conference on Learning Representations, 2018.
  43. Burr Settles. Active learning literature survey. 2009.
  44. Claude Elwood Shannon. A mathematical theory of communication. ACM SIGMOBILE mobile computing and communications review, 5(1):3–55, 2001.
  45. The herbarium challenge 2019 dataset. arXiv preprint arXiv:1906.05372, 2019.
  46. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
  47. Novel class discovery: an introduction and key concepts. arXiv preprint arXiv:2302.12028, 2023.
  48. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  49. Generalized category discovery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7492–7501, 2022a.
  50. Open-set recognition: A good closed-set classifier is all you need. In International Conference on Learning Representations, 2022b.
  51. No representation rules them all in category discovery. In Advances in Neural Information Processing Systems, pages 19962–19989, 2023.
  52. The caltech-ucsd birds-200-2011 dataset. 2011.
  53. A new active labeling method for deep learning. In 2014 International joint conference on neural networks (IJCNN), pages 112–119. IEEE, 2014.
  54. Parametric classification for generalized category discovery: A baseline study. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 16590–16600, 2023.
  55. Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334, 2021.
  56. A comparative survey: Benchmarking for pool-based active learning. In IJCAI, pages 4679–4686, 2021.
  57. A comparative survey of deep active learning. arXiv preprint arXiv:2203.13450, 2022.
  58. Novel class discovery for long-tailed recognition. Transactions on Machine Learning Research, 2023a.
  59. mixup: Beyond empirical risk minimization. In International Conference on Learning Representations, 2018.
  60. Promptcal: Contrastive affinity learning via auxiliary prompts for generalized novel category discovery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3479–3488, 2023b.
  61. Learning semi-supervised gaussian mixture models for generalized category discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 16623–16633, 2023.
  62. Openmix: Reviving known knowledge for discovering novel visual categories in an open world. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9462–9470, 2021.
  63. Prototype augmentation and self-supervision for incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5871–5880, 2021.
  64. Rethinking confidence calibration for failure prediction. In European Conference on Computer Vision, pages 518–536. Springer, 2022.
  65. Open-world machine learning: A review and new outlooks. arXiv preprint arXiv:2403.01759, 2024.
  66. A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1):43–76, 2020.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Shijie Ma (14 papers)
  2. Fei Zhu (49 papers)
  3. Zhun Zhong (60 papers)
  4. Xu-Yao Zhang (44 papers)
  5. Cheng-Lin Liu (71 papers)
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

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