Learning to augment distributions for out-of-distribution detection
Article No.: 3203, Pages 73274 - 73286
Abstract
Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may still fail in the open world, owing to the lack of knowledge about unseen OOD data in advance. Although one can access auxiliary OOD data (distinct from unseen ones) for model training, it remains to analyze how such auxiliary data will work in the open world. To this end, we delve into such a problem from a learning theory perspective, finding that the distribution discrepancy between the auxiliary and the unseen real OOD data is the key to affecting the open-world detection performance. Accordingly, we propose Distributional-Augmented OOD Learning (DAL), alleviating the OOD distribution discrepancy by crafting an OOD distribution set that contains all distributions in a Wasserstein ball centered on the auxiliary OOD distribution. We justify that the predictor trained over the worst OOD data in the ball can shrink the OOD distribution discrepancy, thus improving the open-world detection performance given only the auxiliary OOD data. We conduct extensive evaluations across representative OOD detection setups, demonstrating the superiority of our DAL over its advanced counterparts. The code is publicly available at: https://github.com/tmlr-group/DAL.
Supplementary Material
Supplemental material.
- Download
- 431.26 KB
References
[1]
Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR, 2017.
[2]
Zhen Fang, Yixuan Li, Jie Lu, Jiahua Dong, Bo Han, and Feng Liu. Is out-of-distribution detection learnable? In NeurIPS, 2022.
[3]
Saikiran Bulusu, Bhavya Kailkhura, Bo Li, P Varshney, and Dawn Song. Anomalous instance detection in deep learning: A survey. Technical report, Lawrence Livermore National Lab., 2020.
[4]
Jingkang Yang, Kaiyang Zhou, Yixuan Li, and Ziwei Liu. Generalized out-of-distribution detection: a survey. arXiv preprint arXiv:2110.11334, 2021.
[5]
Tianshi Cao, Chin-Wei Huang, David Yu-Tung Hui, and Joseph Paul Cohen. A benchmark of medical out of distribution detection. arXiv preprint arXiv:2007.04250, 2020.
[6]
Zheyan Shen, Jiashuo Liu, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, and Peng Cui. Towards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624, 2021.
[7]
Dan Hendrycks, Mantas Mazeika, and Thomas G. Dietterich. Deep anomaly detection with outlier exposure. In ICLR, 2019.
[8]
Yifei Ming, Ying Fan, and Yixuan Li. POEM: Out-of-distribution detection with posterior sampling. In ICML, 2022.
[9]
Qizhou Wang, Junjie Ye, Feng Liu, Quanyu Dai, Marcus Kalander, Tongliang Liu, Jianye Hao, and Bo Han. Out-of-distribution detection with implicit outlier transformation. In ICLR, 2023.
[10]
Cédric Villani. Topics in Optimal Transportation. American Mathematical Society, 2021.
[11]
Cédric Villani. Optimal Transport: Old and New. Springer, 2008.
[12]
Xuefeng Du, Zhaoning Wang, Mu Cai, and Yixuan Li. VOS: Learning what you don't know by virtual outlier synthesis. In ICLR, 2022a.
[13]
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, and Jihun Hamm. On certifying and improving generalization to unseen domains. arXiv preprint arXiv:2206.12364, 2022.
[14]
Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, and Somesh Jha. ATOM: Robustifying out-of-distribution detection using outlier mining. In ECML, 2021.
[15]
Kimin Lee, Kibok Lee, Honglak Lee, and Jinwoo Shin. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In NeurIPS, 2018a.
[16]
Weitang Liu, Xiaoyun Wang, John D Owens, and Yixuan Li. Energy-based out-of-distribution detection. In NeurIPS, 2020.
[17]
Yiyou Sun, Yifei Ming, Xiaojin Zhu, and Yixuan Li. Out-of-distribution detection with deep nearest neighbors. In ICML, 2022.
[18]
Aman Sinha, Hongseok Namkoong, and John C. Duchi. Certifying some distributional robustness with principled adversarial training. In ICLR, 2018.
[19]
Hongseok Namkoong and John C. Duchi. Stochastic gradient methods for distributionally robust optimization with f-divergences. In NIPS, 2016.
[20]
Paul Michel, Tatsunori Hashimoto, and Graham Neubig. Modeling the second player in distributionally robust optimization. In ICLR, 2021.
[21]
Matthew Staib and Stefanie Jegelka. Distributionally robust optimization and generalization in kernel methods. In NeurIPS, 2019.
[22]
Rui Dai, Yonggang Zhang, Zhen Fang, Bo Han, and Xinmei Tian. Moderately distributional exploration for domain generalization. In ICML, 2023.
[23]
José H. Blanchet and M. KarthyekRajhaaA. Quantifying distributional model risk via optimal transport. Risk Management eJournal, 2016.
[24]
Alex Krizhevsky and Geoffrey Hinton. Learning multiple layers of features from tiny images. Technical Report TR-2009, University of Toronto, 2009.
[25]
Antonio Torralba, Rob Fergus, and William T Freeman. 80 million tiny images: A large data set for nonparametric object and scene recognition. IEEE transactions on pattern analysis and machine intelligence, 30(11):1958-1970, 2008.
[26]
Mircea Cimpoi, Subhransu Maji, Iasonas Kokkinos, Sammy Mohamed, and Andrea Vedaldi. Describing textures in the wild. In CVPR, 2014.
[27]
Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y Ng. Reading digits in natural images with unsupervised feature learning. In NIPS Workshop, 2011.
[28]
Bolei Zhou, Àgata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6):1452-1464, 2018.
[29]
Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365, 2015.
[30]
Pingmei Xu, Krista A Ehinger, Yinda Zhang, Adam Finkelstein, Sanjeev R Kulkarni, and Jianxiong Xiao. Turkergaze: crowdsourcing saliency with webcam based eye tracking. arXiv preprint arXiv:1504.06755, 2015.
[31]
Sergey Zagoruyko and Nikos Komodakis. Wide residual networks. In BMVC, 2016.
[32]
Ilya Loshchilov and Frank Hutter. SGDR: Stochastic gradient descent with warm restarts. In ICLR, 2017.
[33]
Andrija Djurisic, Nebojsa Bozanic, Arjun Ashok, and Rosanne Liu. Extremely simple activation shaping for out-of-distribution detection. In ICLR, 2023.
[34]
Yiyou Sun, Chuan Guo, and Yixuan Li. ReAct: out-of-distribution detection with rectified activations. In NeurIPS, 2021.
[35]
Jihoon Tack, Sangwoo Mo, Jongheon Jeong, and Jinwoo Shin. CSI: novelty detection via contrastive learning on distributionally shifted instances. In NeurIPS, 2020.
[36]
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. ImageNet: a large-scale hierarchical image database. In CVPR, 2009.
[37]
Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-SNE. Journal of machine learning research, 9(11):2579-2605, 2008.
[38]
Shiyu Liang, Yixuan Li, and R. Srikant. Enhancing the reliability of out-of-distribution image detection in neural networks. In ICLR, 2018.
[39]
Haoran Wang, Weitang Liu, Alex Bocchieri, and Yixuan Li. Can multi-label classification networks know what they don't know? In NeurIPS, 2021a.
[40]
Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. Simple and scalable predictive uncertainty estimation using deep ensembles. In NIPS, 2017.
[41]
Rui Huang and Yixuan Li. MOS: towards scaling out-of-distribution detection for large semantic space. In CVPR, 2021.
[42]
Chandramouli Shama Sastry and Sageev Oore. Detecting out-of-distribution examples with gram matrices. In ICML, 2020.
[43]
Haoqi Wang, Zhizhong Li, Litong Feng, and Wayne Zhang. ViM: Out-of-distribution with virtual-logit matching. In CVPR, 2022a.
[44]
Ziqian Lin, Sreya Dutta Roy, and Yixuan Li. MOOD: Multi-level out-of-distribution detection. In CVPR, 2021.
[45]
Peyman Morteza and Yixuan Li. Provable guarantees for understanding out-of-distribution detection. In AAAI, 2022.
[46]
Yadan Luo, Zijian Wang, Zhuoxiao Chen, Zi Huang, and Mahsa Baktashmotlagh. Source-free progressive graph learning for open-set domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):11240-11255, 2023.
[47]
Rui Huang, Andrew Geng, and Yixuan Li. On the importance of gradients for detecting distributional shifts in the wild. In NeurIPS, 2021.
[48]
Conor Igoe, Youngseog Chung, Ian Char, and Jeff Schneider. How useful are gradients for ood detection really? arXiv preprint arXiv:2205.10439, 2022.
[49]
Jianing Zhu, Hengzhuang Li, Jiangchao Yao, Tongliang Liu, Jianliang Xu, and Bo Han. Unleashing mask: Explore the intrinsic out-of-distribution detection capability. In ICML, 2023a.
[50]
Vikash Sehwag, Mung Chiang, and Prateek Mittal. SSD: A unified framework for self-supervised outlier detection. In ICLR, 2021.
[51]
Haotao Wang, Aston Zhang, Yi Zhu, Shuai Zheng, Mu Li, Alex J Smola, and Zhangyang Wang. Partial and asymmetric contrastive learning for out-of-distribution detection in long-tailed recognition. In ICML, 2022b.
[52]
Haotian Zheng, Qizhou Wang, Zhen Fang, Xiaobo Xia, Feng Liu, Tongliang Liu, and Bo Han. Out-of-distribution detection learning with unreliable out-of-distribution sources. In NeurIPS, 2023.
[53]
Xuefeng Du, Gabriel Gozum, Yifei Ming, and Yixuan Li. SIREN: Shaping representations for detecting out-of-distribution objects. In NeurIPS, 2022b.
[54]
Yifei Ming, Yiyou Sun, Ousmane Dia, and Yixuan Li. How to exploit hyperspherical embeddings for out-of-distribution detection? In ICLR, 2023.
[55]
Alireza Zaeemzadeh, Niccolö Bisagno, Zeno Sambugaro, Nicola Conci, Nazanin Rahnavard, and Mubarak Shah. Out-of-distribution detection using union of 1-dimensional subspaces. In CVPR, 2021.
[56]
Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, and Yixuan Li. Mitigating neural network overconfidence with logit normalization. In ICML, 2022.
[57]
Zhuo Huang, Xiaobo Xia, Li Shen, Bo Han, Mingming Gong, Chen Gong, and Tongliang Liu. Harnessing out-of-distribution examples via augmenting content and style. In ICLR, 2023a.
[58]
Jianing Zhu, Geng Yu, Jiangchao Yao, Tongliang Liu, Gang Niu, Masashi Sugiyama, and Bo Han. Diversified outlier exposure for out-of-distribution detection via informative extrapolation. In NeurIPS, 2023b.
[59]
Yi Li and Nuno Vasconcelos. Background data resampling for outlier-aware classification. In CVPR, 2020.
[60]
Matthias Hein, Maksym Andriushchenko, and Julian Bitterwolf. Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In CVPR, 2019.
[61]
Taewon Jeong and Heeyoung Kim. OOD-MAMl: Meta-learning for few-shot out-of-distribution detection and classification. In NeurIPS, 2020.
[62]
Joost Van Amersfoort, Lewis Smith, Yee Whye Teh, and Yarin Gal. Uncertainty estimation using a single deep deterministic neural network. In ICML, 2020.
[63]
Kimin Lee, Honglak Lee, Kibok Lee, and Jinwoo Shin. Training confidence-calibrated classifiers for detecting out-of-distribution samples. In ICLR, 2018b.
[64]
Sachin Vernekar, Ashish Gaurav, Vahdat Abdelzad, Taylor Denouden, Rick Salay, and Krzysztof Czarnecki. Out-of-distribution detection in classifiers via generation. In NeurIPS Workshop, 2019.
[65]
Leitian Tao, Xuefeng Du, Xiaojin Zhu, and Yixuan Li. Non-parametric outlier synthesis. In ICLR, 2023.
[66]
Yadan Luo, Zijian Wang, Zi Huang, and Mahsa Baktashmotlagh. Progressive graph learning for open-set domain adaptation. In ICML, 2020.
[67]
Lily H. Zhang, Mark Goldstein, and Rajesh Ranganath. Understanding failures in out-of-distribution detection with deep generative models. In ICML, 2021.
[68]
Zhen Fang, Jie Lu, Anjin Liu, Feng Liu, and Guangquan Zhang. Learning bounds for open-set learning. In ICML, 2021.
[69]
Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, and Matthias Hein. Breaking down out-of-distribution detection: Many methods based on OOD training data estimate a combination of the same core quantities. In ICML, 2022.
[70]
Roman Vershynin. High-Dimensional Probability. Springer, 2018.
[71]
Jose Blanchet, Yang Kang, and Karthyek Murthy. Robust wasserstein profile inference and applications to machine learning. Journal of Applied Probability, 56(3):830-857, 2019.
[72]
Noah Golowich, Alexander Rakhlin, and Ohad Shamir. Size-independent sample complexity of neural networks. In COLT, 2018.
[73]
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. In ICLR, 2018.
[74]
Qizhou Wang, Feng Liu, Bo Han, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, and Masashi Sugiyama. Probabilistic margins for instance reweighting in adversarial training. In NeurIPS, 2021b.
[75]
Zhuo Huang, Miaoxi Zhu, Xiaobo Xia, Li Shen, Jun Yu, Chen Gong, Bo Han, Bo Du, and Tongliang Liu. Robust generalization against photon-limited corruptions via worst-case sharpness minimization. In CVPR, 2023b.
[76]
Risheng Liu, Jiaxin Gao, Jin Zhang, Deyu Meng, and Zhouchen Lin. Investigating bi-level optimization for learning and vision from a unified perspective: A survey and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12):10045-10067, 2021.
[77]
Yonggang Zhang, Mingming Gong, Tongliang Liu, Gang Niu, Xinmei Tian, Bo Han, Bernhard Schölkopf, and Kun Zhang. Adversarial robustness through the lens of causality. In ICLR, 2022.
[78]
Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, and Lihi Zelnik-Manor. ImageNet-21k pretraining for the masses. arXiv preprint arXiv:2104.10972, 2021.
[79]
Grant Van Horn, Oisin Mac Aodha, Yang Song, Yin Cui, Chen Sun, Alexander Shepard, Hartwig Adam, Pietro Perona, and Serge J. Belongie. The iNaturalist species classification and detection dataset. In CVPR, 2018.
[80]
Dan Hendrycks, Steven Basart, Mantas Mazeika, Mohammadreza Mostajabi, Jacob Steinhardt, and Dawn Song. Scaling out-of-distribution detection for real-world settings. In ICML, 2022.
Recommendations
Out-of-distribution detection learning with unreliable out-of-distribution sources
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsOut-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open-world classification. However, it is typically hard to collect real out-of-...
Binary coding based label distribution learning
IJCAI'18: Proceedings of the 27th International Joint Conference on Artificial IntelligenceLabel Distribution Learning (LDL) is a novel learning paradigm in machine learning, which assumes that an instance is labeled by a distribution over all labels, rather than labeled by a logic label or some logic labels. Thus, LDL can model the ...
Multi-instance learning with distribution change
AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Artificial IntelligenceMulti-instance learning deals with tasks where each example is a bag of instances, and the bag labels of training data are known whereas instance labels are unknown. Most previous studies on multi-instance learning assumed that the training and testing ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 2023 Neural Information Processing Systems Foundation, Inc.
Publisher
Curran Associates Inc.
Red Hook, NY, United States
Publication History
Published: 30 May 2024
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 24 Sep 2024