Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
121 tokens/sec
GPT-4o
9 tokens/sec
Gemini 2.5 Pro Pro
47 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

PLOOD: Partial Label Learning with Out-of-distribution Objects (2403.06681v4)

Published 11 Mar 2024 in cs.CV

Abstract: Existing Partial Label Learning (PLL) methods posit that training and test data adhere to the same distribution, a premise that frequently does not hold in practical application where Out-of-Distribution (OOD) objects are present. We introduce the OODPLL paradigm to tackle this significant yet underexplored issue. And our newly proposed PLOOD framework enables PLL to tackle OOD objects through Positive-Negative Sample Augmented (PNSA) feature learning and Partial Energy (PE)-based label refinement. The PNSA module enhances feature discrimination and OOD recognition by simulating in- and out-of-distribution instances, which employ structured positive and negative sample augmentation, in contrast to conventional PLL methods struggling to distinguish OOD samples. The PE scoring mechanism combines label confidence with energy-based uncertainty estimation, thereby reducing the impact of imprecise supervision and effectively achieving label disambiguation. Experimental results on CIFAR-10 and CIFAR-100, alongside various OOD datasets, demonstrate that conventional PLL methods exhibit substantial degradation in OOD scenarios, underscoring the necessity of incorporating OOD considerations in PLL approaches. Ablation studies show that PNSA feature learning and PE-based label refinement are necessary for PLOOD to work, offering a robust solution for open-set PLL problems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. On the robustness of average losses for partial-label learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  2. Plmcl: Partial-label momentum curriculum learning for multi-label image classification. In European Conference on Computer Vision, pages 39–55. Springer, 2022.
  3. Candidate-aware selective disambiguation based on normalized entropy for instance-dependent partial-label learning. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pages 1792–1801. IEEE, 2023.
  4. Towards effective visual representations for partial-label learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15589–15598, 2023.
  5. Class-distribution-aware pseudo-labeling for semi-supervised multi-label learning. Advances in Neural Information Processing Systems, 36, 2024.
  6. Consistent complementary-label learning via order-preserving losses. In International Conference on Artificial Intelligence and Statistics, pages 8734–8748. PMLR, 2023.
  7. Self-similarity student for partial label histopathology image segmentation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV 16, pages 117–132. Springer, 2020.
  8. Learning in imperfect environment: Multi-label classification with long-tailed distribution and partial labels. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, pages 1423–1432. IEEE, 2023.
  9. Learning underrepresented classes from decentralized partially labeled medical images. In Medical Image Computing and Computer Assisted Intervention - MICCAI 2022 - 25th International Conference, Singapore, September 18-22, 2022, Proceedings, Part VIII, volume 13438 of Lecture Notes in Computer Science, pages 67–76. Springer, 2022.
  10. Out-of-distribution detection with boundary aware learning. In European Conference on Computer Vision, pages 235–251. Springer, 2022.
  11. Embedding contrastive unsupervised features to cluster in-and out-of-distribution noise in corrupted image datasets. In European Conference on Computer Vision, pages 402–419. Springer, 2022.
  12. Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334, 2021.
  13. Can multi-label classification networks know what they don’t know? Advances in Neural Information Processing Systems, 34:29074–29087, 2021.
  14. Partial label learning: Taxonomy, analysis and outlook. Neural Networks, 2023.
  15. Learning from ambiguously labeled examples. Intelligent Data Analysis, 10(5):419–439, 2006.
  16. Learning from partial labels. The Journal of Machine Learning Research, 12:1501–1536, 2011.
  17. Solving the partial label learning problem: An instance-based approach. In IJCAI, pages 4048–4054, 2015.
  18. Confidence-rated discriminative partial label learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 31, 2017.
  19. Learning from partially supervised data using mixture models and belief functions. Pattern recognition, 42(3):334–348, 2009.
  20. Maximum margin partial label learning. In Asian conference on machine learning, pages 96–111. PMLR, 2016.
  21. Lei Feng and Bo An. Leveraging latent label distributions for partial label learning. In IJCAI, pages 2107–2113, 2018.
  22. Ternary error-correcting output codes based partial label learning algorithm. Journal of Frontiers of Computer Science & Technology, 12(9):1444, 2018.
  23. Partial label learning via feature-aware disambiguation. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1335–1344, 2016.
  24. Gm-pll: Graph matching based partial label learning. IEEE Transactions on Knowledge and Data Engineering, 33(2):521–535, 2019.
  25. Adaptive graph guided disambiguation for partial label learning. IEEE Trans. Pattern Anal. Mach. Intell., 44(12):8796–8811, 2022.
  26. Graphdpi: Partial label disambiguation by graph representation learning via mutual information maximization. Pattern Recognition, 134:109133, 2023.
  27. Complementary classifier induced partial label learning. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, page 974–983, 2023.
  28. Partial-label and structure-constrained deep coupled factorization network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 10948–10955, 2021.
  29. Deep graph matching for partial label learning. In Proceedings of the International Joint Conference on Artificial Intelligence, pages 3306–3312, 2022.
  30. Towards effective visual representations for partial-label learning. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023, pages 15589–15598. IEEE, 2023.
  31. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690, 2017.
  32. Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10951–10960, 2020.
  33. Feature space singularity for out-of-distribution detection. arXiv preprint arXiv:2011.14654, 2020.
  34. Energy-based out-of-distribution detection. Advances in neural information processing systems, 33:21464–21475, 2020.
  35. Out-of-distribution detection using union of 1-dimensional subspaces. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 9452–9461, 2021.
  36. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31, 2018.
  37. React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems, 34:144–157, 2021.
  38. Mos: Towards scaling out-of-distribution detection for large semantic space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8710–8719, 2021.
  39. Mood: Multi-level out-of-distribution detection. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 15313–15323, 2021.
  40. Codes: Chamfer out-of-distribution examples against overconfidence issue. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1153–1162, 2021.
  41. Out-of-distribution detection in classifiers via generation. arXiv preprint arXiv:1910.04241, 2019.
  42. Multi-label out-of-distribution detection via exploiting sparsity and co-occurrence of labels. Image and Vision Computing, 126:104548, 2022.
  43. Ovae: Out-of-distribution detection with multi-label-enhanced variational autoencoders. In CCF Conference on Big Data, pages 233–247. Springer, 2022.
  44. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136, 2016.
  45. Scaling out-of-distribution detection for real-world settings. arXiv preprint arXiv:1911.11132, 2019.
  46. Entropy maximization and meta classification for out-of-distribution detection in semantic segmentation. In Proceedings of the ieee/cvf international conference on computer vision, pages 5128–5137, 2021.
  47. Towards open set deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1563–1572, 2016.
  48. A simple fix to mahalanobis distance for improving near-ood detection. arXiv preprint arXiv:2106.09022, 2021.
  49. Decoupling maxlogit for out-of-distribution detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3388–3397, 2023.

Summary

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

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