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

MOODv2: Masked Image Modeling for Out-of-Distribution Detection (2401.02611v1)

Published 5 Jan 2024 in cs.CV

Abstract: The crux of effective out-of-distribution (OOD) detection lies in acquiring a robust in-distribution (ID) representation, distinct from OOD samples. While previous methods predominantly leaned on recognition-based techniques for this purpose, they often resulted in shortcut learning, lacking comprehensive representations. In our study, we conducted a comprehensive analysis, exploring distinct pretraining tasks and employing various OOD score functions. The results highlight that the feature representations pre-trained through reconstruction yield a notable enhancement and narrow the performance gap among various score functions. This suggests that even simple score functions can rival complex ones when leveraging reconstruction-based pretext tasks. Reconstruction-based pretext tasks adapt well to various score functions. As such, it holds promising potential for further expansion. Our OOD detection framework, MOODv2, employs the masked image modeling pretext task. Without bells and whistles, MOODv2 impressively enhances 14.30% AUROC to 95.68% on ImageNet and achieves 99.98% on CIFAR-10.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. R. Caruana, Y. Lou, J. Gehrke, P. Koch, M. Sturm, and N. Elhadad, “Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission,” in Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, 2015, pp. 1721–1730.
  2. C. Phua, V. Lee, K. Smith, and R. Gayler, “A comprehensive survey of data mining-based fraud detection research,” arXiv preprint arXiv:1009.6119, 2010.
  3. K. Eykholt, I. Evtimov, E. Fernandes, B. Li, A. Rahmati, C. Xiao, A. Prakash, T. Kohno, and D. Song, “Robust physical-world attacks on deep learning visual classification,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 1625–1634.
  4. J. Tack, S. Mo, J. Jeong, and J. Shin, “Csi: Novelty detection via contrastive learning on distributionally shifted instances,” Advances in neural information processing systems, vol. 33, pp. 11 839–11 852, 2020.
  5. V. Sehwag, M. Chiang, and P. Mittal, “Ssd: A unified framework for self-supervised outlier detection,” arXiv preprint arXiv:2103.12051, 2021.
  6. S. Fort, J. Ren, and B. Lakshminarayanan, “Exploring the limits of out-of-distribution detection,” Advances in Neural Information Processing Systems, vol. 34, pp. 7068–7081, 2021.
  7. H. Wang, Z. Li, L. Feng, and W. Zhang, “Vim: Out-of-distribution with virtual-logit matching,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
  8. J. Yang, K. Zhou, Y. Li, and Z. Liu, “Generalized out-of-distribution detection: A survey,” arXiv preprint arXiv:2110.11334, 2021.
  9. M. B. Sariyildiz, K. Alahari, D. Larlus, and Y. Kalantidis, “Fake it till you make it: Learning transferable representations from synthetic imagenet clones,” 2023.
  10. A. Saha, A. Subramanya, and H. Pirsiavash, “Hidden trigger backdoor attacks,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 11 957–11 965, Apr. 2020. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/6871
  11. ——, “Hidden trigger backdoor attacks,” in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 07, 2020, pp. 11 957–11 965.
  12. H. Bao, L. Dong, and F. Wei, “Beit: Bert pre-training of image transformers,” arXiv preprint arXiv:2106.08254, 2021.
  13. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
  14. K. He, X. Chen, S. Xie, Y. Li, P. Dollár, and R. Girshick, “Masked autoencoders are scalable vision learners,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16 000–16 009.
  15. D. Hendrycks and K. Gimpel, “A baseline for detecting misclassified and out-of-distribution examples in neural networks,” arXiv preprint arXiv:1610.02136, 2016.
  16. D. Hendrycks, S. Basart, M. Mazeika, A. Zou, J. Kwon, M. Mostajabi, J. Steinhardt, and D. Song, “Scaling out-of-distribution detection for real-world settings,” arXiv preprint arXiv:1911.11132, 2019.
  17. W. Liu, X. Wang, J. Owens, and Y. Li, “Energy-based out-of-distribution detection,” Advances in neural information processing systems, vol. 33, pp. 21 464–21 475, 2020.
  18. Y. Sun, C. Guo, and Y. Li, “React: Out-of-distribution detection with rectified activations,” Advances in Neural Information Processing Systems, vol. 34, pp. 144–157, 2021.
  19. K. Lee, K. Lee, H. Lee, and J. Shin, “A simple unified framework for detecting out-of-distribution samples and adversarial attacks,” Advances in neural information processing systems, vol. 31, 2018.
  20. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
  21. X. Chen, S. Xie, and K. He, “An empirical study of training self-supervised vision transformers,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2021, pp. 9640–9649.
  22. M. Oquab, T. Darcet, T. Moutakanni, H. Vo, M. Szafraniec, V. Khalidov, P. Fernandez, D. Haziza, F. Massa, A. El-Nouby, M. Assran, N. Ballas, W. Galuba, R. Howes, P.-Y. Huang, S.-W. Li, I. Misra, M. Rabbat, V. Sharma, G. Synnaeve, H. Xu, H. Jegou, J. Mairal, P. Labatut, A. Joulin, and P. Bojanowski, “Dinov2: Learning robust visual features without supervision,” 2023.
  23. Z. Peng, L. Dong, H. Bao, Q. Ye, and F. Wei, “Beit v2: Masked image modeling with vector-quantized visual tokenizers,” 2022.
  24. I. Ndiour, N. Ahuja, and O. Tickoo, “Out-of-distribution detection with subspace techniques and probabilistic modeling of features,” arXiv preprint arXiv:2012.04250, 2020.
  25. K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, “Momentum contrast for unsupervised visual representation learning,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 9729–9738.
  26. Y. Li, Y. Jiang, Z. Li, and S.-T. Xia, “Backdoor learning: A survey,” IEEE Transactions on Neural Networks and Learning Systems, 2022.
  27. T. DeVries and G. W. Taylor, “Learning confidence for out-of-distribution detection in neural networks,” arXiv preprint arXiv:1802.04865, 2018.
  28. A. Zaeemzadeh, N. Bisagno, Z. Sambugaro, N. Conci, N. Rahnavard, and M. Shah, “Out-of-distribution detection using union of 1-dimensional subspaces,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 9452–9461.
  29. R. Huang and Y. Li, “MOS: Towards scaling out-of-distribution detection for large semantic space,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8710–8719.
  30. J. Li, P. Chen, Z. He, S. Yu, S. Liu, and J. Jia, “Rethinking out-of-distribution (ood) detection: Masked image modeling is all you need,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 11 578–11 589.
  31. I. Krasin, T. Duerig, N. Alldrin, V. Ferrari, S. Abu-El-Haija, A. Kuznetsova, H. Rom, J. Uijlings, S. Popov, A. Veit, S. Belongie, V. Gomes, A. Gupta, C. Sun, G. Chechik, D. Cai, Z. Feng, D. Narayanan, and K. Murphy, “Openimages: A public dataset for large-scale multi-label and multi-class image classification.” Dataset available from https://github.com/openimages, 2017.
  32. M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, and A. Vedaldi, “Describing textures in the wild,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 3606–3613.
  33. G. Van Horn, O. Mac Aodha, Y. Song, Y. Cui, C. Sun, A. Shepard, H. Adam, P. Perona, and S. Belongie, “The inaturalist species classification and detection dataset,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8769–8778.
  34. D. Hendrycks, K. Zhao, S. Basart, J. Steinhardt, and D. Song, “Natural adversarial examples,” CVPR, 2021.
  35. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. S. Bernstein, A. C. Berg, and F. Li, “Imagenet large scale visual recognition challenge,” Int. J. Comput. Vis., 2015.
  36. M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, and A. Vedaldi, “Describing textures in the wild,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 3606–3613.
  37. G. Van Horn, O. Mac Aodha, Y. Song, Y. Cui, C. Sun, A. Shepard, H. Adam, P. Perona, and S. Belongie, “The iNaturalist species classification and detection dataset,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8769–8778.
  38. D. Hendrycks, K. Zhao, S. Basart, J. Steinhardt, and D. Song, “Natural adversarial examples,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15 262–15 271.
  39. A. Krizhevsky, G. Hinton et al., “Learning multiple layers of features from tiny images,” 2009.
  40. B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba, “Places: A 10 million image database for scene recognition,” IEEE transactions on pattern analysis and machine intelligence, vol. 40, no. 6, pp. 1452–1464, 2017.
  41. S. Liang, Y. Li, and R. Srikant, “Enhancing the reliability of out-of-distribution image detection in neural networks,” arXiv preprint arXiv:1706.02690, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Jingyao Li (18 papers)
  2. Pengguang Chen (20 papers)
  3. Shaozuo Yu (11 papers)
  4. Shu Liu (146 papers)
  5. Jiaya Jia (162 papers)
Citations (4)
View on Semantic Scholar

Summary

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

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