skip to main content
research-article

MixOOD: Improving Out-of-distribution Detection with Enhanced Data Mixup

Authors Info & Claims
Published:16 March 2023Publication History
Skip Abstract Section

Abstract

Detecting out-of-distribution (OOD) inputs for deep learning models is a critical task when models are deployed in real-world environments. Recently, a large number of works have been dedicated to tackling the OOD detection problem. One of the most straightforward and effective ways is OOD training, which adds heterogeneous auxiliary data in the training stage. However, the extra auxiliary data cannot be involved arbitrarily. A high-quality and powerful auxiliary dataset must contain samples that belong to OOD but are close to in-distribution (ID), which can teach the model to learn more information about OOD samples, furthermore, distinguish OOD from ID. The key issue for this problem is how to simply acquire such distinctive OOD samples. In this article, we propose an enhanced Mixup-based OOD (MixOOD) detection strategy that can be attached to any threshold-based OOD detecting method. Different from the traditional Mixup designed for ID data augmentation, our proposed MixOOD generates augmented images with deliberately modified Mixup and then uses them as auxiliary OOD data to leverage the OOD detection. We test our method with classical OOD detecting approaches like Maximum Softmax Probability, Energy Score, and Out-of-distribution detector for Neural networks. Experiments show that models with MixOOD can better distinguish in- and out-of-distribution samples than the original version of each approach.

REFERENCES

  1. [1] Krizhevsky Alex, Sutskever Ilya, and Hinton Geoffrey E.. 2012. Imagenet classification with deep convolutional neural networks. Adv. Neural Info. Process. Syst. 25 (2012).Google ScholarGoogle Scholar
  2. [2] LeCun Yann, Bottou Léon, Bengio Yoshua, and Haffner Patrick. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 22782324.Google ScholarGoogle Scholar
  3. [3] Ge Zheng, Liu Songtao, Wang Feng, Li Zeming, and Sun Jian. 2021. Yolox: Exceeding yolo series in 2021. Retrieved from https://arXiv:2107.08430.Google ScholarGoogle Scholar
  4. [4] Tan Mingxing and Le Quoc. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 61056114.Google ScholarGoogle Scholar
  5. [5] Liu Weitang, Wang Xiaoyun, Owens John, and Li Yixuan. 2020. Energy-based out-of-distribution detection. Adv Neural Info. Process. Syst. 33 (2020), 2146421475.Google ScholarGoogle Scholar
  6. [6] Hendrycks Dan and Gimpel Kevin. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In Proceedings of the International Conference on Learning Representations.Google ScholarGoogle Scholar
  7. [7] Netzer Yuval, Wang Tao, Coates Adam, Bissacco Alessandro, Wu Bo, and Ng Andrew Y. 2011. Reading digits in natural images with unsupervised feature learning. In Proceedings of the Conference on Neural Information Processing Workshops.Google ScholarGoogle Scholar
  8. [8] Liang Shiyu, Li Yixuan, and Srikant Rayadurgam. 2017. Enhancing the reliability of out-of-distribution image detection in neural networks. Retrieved from https://arXiv:1706.02690.Google ScholarGoogle Scholar
  9. [9] Hendrycks Dan, Mazeika Mantas, and Dietterich Thomas. 2019. Deep anomaly detection with outlier exposure. In Proceedings of the International Conference on Learning Representations.Google ScholarGoogle Scholar
  10. [10] Lee Kimin, Lee Honglak, Lee Kibok, and Shin Jinwoo. 2017. Training confidence-calibrated classifiers for detecting out-of-distribution samples. Retrieved from https://arXiv:1711.09325.Google ScholarGoogle Scholar
  11. [11] al. Johnson et1996. Tiny Imagenet Visual Recognition Challenge. Website. Retrieved from https://tiny-imagenet.herokuapp.com.Google ScholarGoogle Scholar
  12. [12] Zhang Hongyi, Cisse Moustapha, Dauphin Yann N., and Lopez-Paz David. 2017. mixup: Beyond empirical risk minimization. Retrieved from https://arXiv:1710.09412.Google ScholarGoogle Scholar
  13. [13] Yun Sangdoo, Han Dongyoon, Chun Sanghyuk, Oh Seong Joon, Yoo Youngjoon, and Choe Junsuk. 2019. CutMix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of IEEE International Conference on Computer Vision. 60226031. DOI:Google ScholarGoogle ScholarCross RefCross Ref
  14. [14] LeCun Yann, Chopra Sumit, Hadsell Raia, Ranzato M., and Huang F.. 2006. A tutorial on energy-based learning. Predict. Struct. Data 1, 0 (2006).Google ScholarGoogle Scholar
  15. [15] Chen Guangyao, Peng Peixi, Wang Xiangqian, and Tian Yonghong. 2021. Adversarial reciprocal points learning for open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44 (2021), 8065–8081. DOI:Google ScholarGoogle ScholarCross RefCross Ref
  16. [16] Ravikumar Deepak, Kodge Sangamesh, Garg Isha, and Roy Kaushik. 2021. Intra-class mixup for out-of-distribution detection. Retrieved from https://openreview.net/forum?id=HRL6el2SBQ.Google ScholarGoogle Scholar
  17. [17] Vaze Sagar, Han Kai, Vedaldi Andrea, and Zisserman Andrew. 2021. Open-set recognition: A good closed-set classifier is all you need. Retrieved from https://arXiv:2110.06207.Google ScholarGoogle Scholar
  18. [18] Sun Yi-Xuan and Wang Wei. 2022. Exploiting mixed unlabeled data for detecting samples of seen and unseen out-of-distribution classes. In Proceedings of the AAAI Conference on Artificial Intelligence.Google ScholarGoogle ScholarCross RefCross Ref
  19. [19] Zhang Jingyang, Inkawhich Nathan, Chen Yiran, and Li Hai. 2021. Fine-grained out-of-distribution detection with mixup outlier exposure. Retrieved from https://arXiv:2106.03917.Google ScholarGoogle Scholar
  20. [20] Mehta Deval, Gal Yaniv, Bowling Adrian, Bonnington Paul, and Ge Zongyuan. 2022. Out-of-distribution detection for long-tailed and fine-grained skin lesion images. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 732742.Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Shorten Connor and Khoshgoftaar Taghi M.. 2019. A survey on image data augmentation for deep learning. J. Big Data 6, 1 (2019), 148.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] McInnes Leland, Healy John, Saul Nathaniel, and Grossberger Lukas. 2018. UMAP: Uniform manifold approximation and projection. J. Open Source Softw. 3, 29 (2018), 861.Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] Krizhevsky Alex. 2009. Learning multiple layers of features from tiny images. Master’s Thesis. University of Toronto.Google ScholarGoogle Scholar
  24. [24] Yu Fisher, Seff Ari, Zhang Yinda, Song Shuran, Funkhouser Thomas, and Xiao Jianxiong. 2015. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. Retrieved from https://arXiv:1506.03365.Google ScholarGoogle Scholar
  25. [25] Cimpoi Mircea, Maji Subhransu, Kokkinos Iasonas, Mohamed Sammy, and Vedaldi Andrea. 2014. Describing textures in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 36063613.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Xu Pingmei, Ehinger Krista A., Zhang Yinda, Finkelstein Adam, Kulkarni Sanjeev R., and Xiao Jianxiong. 2015. Turkergaze: Crowdsourcing saliency with webcam based eye tracking. Retrieved from https://arXiv:1504.06755.Google ScholarGoogle Scholar
  27. [27] Deng Jia, Dong Wei, Socher Richard, Li Li-Jia, Li Kai, and Fei-Fei Li. 2009. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 248255.Google ScholarGoogle ScholarCross RefCross Ref
  28. [28] Huang Gao, Liu Zhuang, Maaten Laurens Van Der, and Weinberger Kilian Q.. 2017. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 47004708.Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Duchi John, Hazan Elad, and Singer Yoram. 2011. Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 7 (2011).Google ScholarGoogle Scholar
  30. [30] Da Kingma. 2014. A method for stochastic optimization. Retrieved from https://arXiv:1412.6980.Google ScholarGoogle Scholar
  31. [31] Vyas Apoorv, Jammalamadaka Nataraj, Zhu Xia, Das Dipankar, Kaul Bharat, and Willke Theodore L.. 2018. Out-of-distribution detection using an ensemble of self supervised leave-out classifiers. In Proceedings of the European Conference on Computer Vision. 550564.Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Zagoruyko Sergey and Komodakis Nikos. 2016. Wide residual networks. Retrieved from https://arXiv:1605.07146.Google ScholarGoogle Scholar
  33. [33] Ahmed Faruk and Courville Aaron. 2020. Detecting semantic anomalies. In Proceedings of the AAAI Conference on Artificial Intelligence.Google ScholarGoogle ScholarCross RefCross Ref
  34. [34] Maji Subhransu, Rahtu Esa, Kannala Juho, Blaschko Matthew, and Vedaldi Andrea. 2013. Fine-grained visual classification of aircraft. Retrieved from https://arXiv:1306.5151.Google ScholarGoogle Scholar
  35. [35] Krause Jonathan, Stark Michael, Deng Jia, and Fei-Fei Li. 2013. 3D object representations for fine-grained categorization. In Proceedings of IEEE International Conference on Computer Vision workshops. 554561.Google ScholarGoogle ScholarDigital LibraryDigital Library
  36. [36] Chen Tianshui, Wu Wenxi, Gao Yuefang, Dong Le, Luo Xiaonan, and Lin Liang. 2018. Fine-grained representation learning and recognition by exploiting hierarchical semantic embedding. In Proceedings of the ACM International Conference on Multimedia. 20232031.Google ScholarGoogle ScholarDigital LibraryDigital Library
  37. [37] Horn Grant Van, Branson Steve, Farrell Ryan, Haber Scott, Barry Jessie, Ipeirotis Panos, Perona Pietro, and Belongie Serge. 2015. Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 595604.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. MixOOD: Improving Out-of-distribution Detection with Enhanced Data Mixup

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access

    • Published in

      cover image ACM Transactions on Multimedia Computing, Communications, and Applications
      ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 19, Issue 5
      September 2023
      262 pages
      ISSN:1551-6857
      EISSN:1551-6865
      DOI:10.1145/3585398
      • Editor:
      • Abdulmotaleb El Saddik
      Issue’s Table of Contents

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 16 March 2023
      • Online AM: 4 January 2023
      • Accepted: 23 December 2022
      • Revised: 25 October 2022
      • Received: 5 May 2022
      Published in tomm Volume 19, Issue 5

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article
    • Article Metrics

      • Downloads (Last 12 months)468
      • Downloads (Last 6 weeks)39

      Other Metrics

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    View Full Text

    HTML Format

    View this article in HTML Format .

    View HTML Format
    About Cookies On This Site

    We use cookies to ensure that we give you the best experience on our website.

    Learn more

    Got it!