Abstract
Deep neural networks suffer from the overconfidence issue in the open world, meaning that classifiers could yield confident, incorrect predictions for out-of-distribution (OOD) samples. It is an urgent and challenging task to detect these samples drawn far away from training distribution based on the security considerations of artificial intelligence. Many existing methods based on neural networks mainly rely on complex processing strategies, such as temperature scaling and input preprocessing, to obtain satisfactory results. In this paper, we propose an effective algorithm for detecting out-of-distribution examples utilizing PEDCC-Loss. We mathematically analyze the nature of the confidence score output by the PEDCC (Predefined Evenly-Distribution Class Centroids) classifier and then construct a more effective scoring function to distinguish in-distribution (ID) and out-of-distribution samples. In this method, there is no need to preprocess the input samples and the computational burden of the algorithm is reduced. Experiments demonstrate that our method can achieve better OOD detection performance than Softmax-based methods.
Similar content being viewed by others
References
Amodei D, Olah C, Steinhardt J, Christiano P, Schulman J, Mané D (2016) Concrete problems in ai safety. arXiv preprint arXiv:1606.06565
Andrews J, Tanay T, Morton EJ, Griffin LD (2016) Transfer representation-learning for anomaly detection. JMLR
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei, L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition pp 248–255. Ieee
Evtimov I, Eykholt K, Fernandes E, Kohno T, Li B, Prakash A, Rahmati A, Song D (2017) Robust physical-world attacks on machine learning models. 2(3):4 arXiv preprint arXiv:1707.08945
Fawcett T (2006) An introduction to roc analysis. Pattern recognit lett 27(8):861–874
Gawlikowski J, Tassi CRN, Ali M, Lee J, Humt M, Feng J, Kruspe A, Triebel R, Jung P, Roscher R et al. (2021) A survey of uncertainty in deep neural networks. arXiv preprint arXiv:2107.03342
He K, Zhang X, Ren S, Sun J (June 2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hendrycks D, Gimpel K (2017) A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net
Hsu Y-C, Shen Y, Jin H, Kira Z (2020) 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, pp 10951–10960
Hu H, Yan Y, Zhu Q, Zheng G (2021) Generation and frame characteristics of predefined evenly-distributed class centroids for pattern classification. IEEE Access
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition pp 4700–4708
Krizhevsky A, Hinton G et al. (2009) Learning multiple layers of features from tiny images
Lee K, Lee H, Lee K, Shin J (2017) Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint arXiv:1711.09325
Lee K, Lee K, Lee H, Shin J (2018) A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: Advances in Neural Information Processing Systems, pp 7167–7177
Liang S, Li Y, Srikant R (2017) Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690
Malinin A, Gales M (2019) Reverse kl-divergence training of prior networks: Improved uncertainty and adversarial robustness. In: NeurIPS
Malinin A, Gales MJF (2018) Predictive uncertainty estimation via prior networks. In: NeurIPS pp 7047–7058
Masana M, Ruiz I, Serrat J, van de Weijer J, Lopez AM (2018) Metric learning for novelty and anomaly detection. arXiv preprint arXiv:1808.05492
Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning
Sharif M, Bhagavatula S, Bauer L, Reiter MK (2016) Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition. In: Proceedings of the 2016 acm sigsac conference on computer and communications security pp 1528–1540 (2016)
Wang F, Cheng J, Liu W, Liu H (2018) Additive margin softmax for face verification. IEEE Signal Process Lett 25(7):926–930
Yu F, Seff A, Zhang Y, Song S, Funkhouser T, Xiao J (2015) Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365
Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv preprint arXiv:1605.07146
Zhang X, Cui P, Xu R, Zhou L, He Y, Shen Z (2021) Deep stable learning for out-of-distribution generalization. arXiv preprint arXiv:2104.07876
Zhu Q-Y, Li T-T (2020) Semi-supervised learning method based on predefined evenly-distributed class centroids. Applied Intelligence 1–9
Zhu Q, He Z, Ye X (2019) Incremental classifier learning based on pedcc-loss and cosine distance. arXiv preprint arXiv:1906.04734
Zhu Qi, Wang Z (2020) An image clustering auto-encoder based on predefined evenly-distributed class centroids and mmd distance. Neural Processing Letters 1–16
Zhu Qiuyu, Zhang Pengju, Wang Zhengyong, Ye Xin (2019) A new loss function for cnn classifier based on predefined evenly-distributed class centroids. IEEE Access 8:10888–10895
Zhu Q, Zhang R (2019) A classification supervised auto-encoder based on predefined evenly-distributed class centroids. arXiv preprint arXiv:1902.00220
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declared that they have no conflicts of interest to this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhu, Q., Zheng, G. & Yan, Y. Effective Out-of-Distribution Detection in Classifier Based on PEDCC-Loss. Neural Process Lett 55, 1937–1949 (2023). https://doi.org/10.1007/s11063-022-10970-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10970-y