Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery (2404.08995v4)

Published 13 Apr 2024 in cs.LG, cs.AI, and cs.CV

Abstract: Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come from known or novel classes. The prevailing approach generally involves clustering across all data and learning conceptions by prototypical contrastive learning. However, existing methods largely hinge on the performance of clustering algorithms and are thus subject to their inherent limitations. Firstly, the estimated cluster number is often smaller than the ground truth, making the existing methods suffer from the lack of prototypes for comprehensive conception learning. To address this issue, we propose an adaptive probing mechanism that introduces learnable potential prototypes to expand cluster prototypes (centers). As there is no ground truth for the potential prototype, we develop a self-supervised prototype learning framework to optimize the potential prototype in an end-to-end fashion. Secondly, clustering is computationally intensive, and the conventional strategy of clustering both labelled and unlabelled instances exacerbates this issue. To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes. Despite the simplicity of our proposed method, extensive empirical analysis on a wide range of datasets confirms that our method consistently delivers state-of-the-art results. Specifically, our method surpasses the nearest competitor by a significant margin of 9.7% within the Stanford Cars dataset and 12x clustering efficiency within the Herbarium 19 dataset. We will make the code and checkpoints publicly available at https://github.com/xjtuYW/PNP.git.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Transfer and alignment network for generalized category discovery. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 10856–10864, 2024.
  2. Generalized category discovery with decoupled prototypical network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 12527–12535, 2023.
  3. Masked siamese networks for label-efficient learning. In European Conference on Computer Vision, pages 456–473. Springer, 2022.
  4. Semi-supervised learning of visual features by non-parametrically predicting view assignments with support samples. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8443–8452, 2021.
  5. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019.
  6. Open-world semi-supervised learning, 2021.
  7. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, 33:9912–9924, 2020.
  8. Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9650–9660, 2021.
  9. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  10. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  11. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR, 2021.
  12. A unified objective for novel class discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9284–9292, 2021.
  13. Towards discovery and attribution of open-world gan generated images. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14094–14103, 2021.
  14. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33:21271–21284, 2020.
  15. Autonovel: Automatically discovering and learning novel visual categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10):6767–6781, 2021.
  16. 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.
  17. CiPR: An efficient framework with cross-instance positive relations for generalized category discovery. Transactions on Machine Learning Research, 2024.
  18. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738, 2020.
  19. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  20. Learning to cluster in order to transfer across domains and tasks. In International Conference on Learning Representations, 2018.
  21. Multi-class classification without multi-class labels. arXiv preprint arXiv:1901.00544, 2019.
  22. Deep clustering by semantic contrastive learning. arXiv preprint arXiv:2103.02662, 2021.
  23. Joint representation learning and novel category discovery on single-and multi-modal data. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 610–619, 2021.
  24. Billion-scale similarity search with gpus. IEEE Transactions on Big Data, 7(3):535–547, 2019.
  25. Proxy anchor-based unsupervised learning for continuous generalized category discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16688–16697, 2023.
  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. Prototypical contrastive learning of unsupervised representations. arXiv preprint arXiv:2005.04966, 2020.
  29. SGDR: Stochastic gradient descent with warm restarts. In International Conference on Learning Representations, 2017.
  30. Active generalized category discovery. arXiv preprint arXiv:2403.04272, 2024.
  31. 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, volume 1, pages 281–297. Oakland, CA, USA, 1967.
  32. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151, 2013.
  33. Semi-supervised learning. MIT Press, 2006.
  34. Cats and dogs. In 2012 IEEE conference on computer vision and pattern recognition, pages 3498–3505. IEEE, 2012.
  35. 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.
  36. Learn to categorize or categorize to learn? self-coding for generalized category discovery. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  37. Maps of random walks on complex networks reveal community structure. Proceedings of the national academy of sciences, 105(4):1118–1123, 2008.
  38. The herbarium challenge 2019 dataset. arXiv preprint arXiv:1906.05372, 2019.
  39. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  40. Generalized category discovery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7492–7501, 2022.
  41. Open-set recognition: a good closed-set classifier is all you need? In International Conference on Learning Representations, 2022.
  42. No representation rules them all in category discovery. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  43. The caltech-ucsd birds-200-2011 dataset. california institute of technology, 2011.
  44. SPTNet: An efficient alternative framework for generalized category discovery with spatial prompt tuning. In The Twelfth International Conference on Learning Representations, 2024.
  45. Parametric classification for generalized category discovery: A baseline study. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16590–16600, 2023.
  46. Metagcd: Learning to continually learn in generalized category discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1655–1665, 2023.
  47. Generalized category discovery with clustering assignment consistency. In International Conference on Neural Information Processing, pages 535–547. Springer, 2023.
  48. 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, 2023.
  49. Novel visual category discovery with dual ranking statistics and mutual knowledge distillation. Advances in Neural Information Processing Systems, 34:22982–22994, 2021.
  50. Incremental generalized category discovery. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 19137–19147, 2023.
  51. Learning semi-supervised gaussian mixture models for generalized category discovery. arXiv preprint arXiv:2305.06144, 2023.
  52. Neighborhood contrastive learning for novel class discovery. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10867–10875, 2021.
Citations (2)
View on Semantic Scholar

Summary

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

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

Tweets