{"type":"ScholarlyArticle","title":"Convolutional Neural Networks with Compression Complexity Pooling for Out-of-Distribution Image Detection","authors":[{"name":"Sehun Yu","slug":"sehun-yu","given":"Sehun","family":"Yu","affiliation":"Pohang University of Science and Technology (POSTECH) , Pohang , Korea"},{"name":"Dongha Lee","slug":"dongha-lee","given":"Dongha","family":"Lee","affiliation":"Pohang University of Science and Technology (POSTECH) , Pohang , Korea"},{"name":"Hwanjo Yu","slug":"hwanjo-yu","given":"Hwanjo","family":"Yu","affiliation":"Pohang University of Science and Technology (POSTECH) , Pohang , Korea"}],"abstract":"To reliably detect out-of-distribution images based on already deployed convolutional neural networks, several recent studies on the out-of-distribution detection have tried to define effective confidence scores without retraining the model. Although they have shown promising results, most of them need to find the optimal hyperparameter values by using a few out-of-distribution images, which eventually assumes a specific test distribution and makes it less practical for real-world applications. In this work, we propose a novel out-of-distribution detection method termed as MALCOM, which neither uses any out-of-distribution sample nor retrains the model. Inspired by an observation that the global average pooling cannot capture spatial information of feature maps in convolutional neural networks, our method aims to extract informative sequential patterns from the feature maps. To this end, we introduce a similarity metric that focuses on shared patterns between two sequences based on the normalized compression distance. In short, MALCOM uses both the global average and the spatial patterns of feature maps to identify out-of-distribution images accurately.","doi":"10.24963/ijcai.2020/337","url":"https://ijcai.org/proceedings/2020/337","pdf":"https://ijcai.org/proceedings/2020/0337.pdf","markdown":"https://ijcai.org/proceedings/2020/337.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/337","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":337,"pages":{"first":2435,"last":2441},"keywords":["Machine Learning: Deep Learning: Convolutional networks","Uncertainty in AI: Other"],"videos":[],"references":[{"position":1,"raw":"[Barata and Hussein, 2012] João Carlos Alves Barata and Mahir Saleh Hussein. The moore-penrose pseudoinverse: A tutorial review of the theory. Brazilian Journal of Physics, 42(1-2):146-165, 2012.","title":"The moore-penrose pseudoinverse: A tutorial review of the theory","authors":"Hussein ; Barata, João Carlos, Alves Barata, Mahir Saleh, Hussein","year":"2012","venue":"Brazilian Journal of Physics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berek et al., 2014] Petr Berek, Michal Prilepok, Jan Platos, and Vaclav Snasel. Classification of eeg signals using vec- tor quantization. In ICAISC, pages 107-118. Springer, 2014.","title":"Classification of eeg signals using vector quantization","authors":"Berek","year":"2014","venue":"ICAISC","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Borbely, 2016] Rebecca Schuller Borbely. On normalized compression distance and large malware. Journal of Com- puter Virology and Hacking Techniques, 12(4):235-242, 2016.","title":"On normalized compression distance and large malware","authors":"Rebecca Schuller, Borbely","year":"2016","venue":"Journal of Computer Virology and Hacking Techniques","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cilibrasi and Vitányi, 2005] Rudi Cilibrasi and Paul MB Vitányi. Clustering by compression. IEEE Transactions on Information theory, 51(4):1523-1545, 2005.","title":"Rudi Cilibrasi and Paul MB Vitányi. Clustering by compression","authors":"Vitányi Cilibrasi","year":"2005","venue":"IEEE Transactions on Information theory","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Coltuc et al., 2018] Dinu Coltuc, Mihai Datcu, and Daniela Coltuc. On the use of normalized compression distances for image similarity detection. Entropy, 20(2):99, 2018.","title":"On the use of normalized compression distances for image similarity detection","authors":"Dinu Coltuc, Mihai Datcu, Daniela Coltuc","year":"2018","venue":"Entropy","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Guha and Ward, 2014] Tanaya Guha and Rabab K Ward. Image similarity using sparse representation and com- pression distance. IEEE Transactions on Multimedia, 16(4):980-987, 2014.","title":"Image similarity using sparse representation and compression distance","authors":"Tanaya Guha, K Rabab, Ward","year":"2014","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hendrycks and Gimpel, 2017] Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and out-of- distribution examples in neural networks. In ICLR, 2017.","title":"A baseline for detecting misclassified and out-ofdistribution examples in neural networks","authors":"Gimpel Hendrycks, Dan Hendrycks, Kevin Gimpel","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2017] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. Densely con- nected convolutional networks. In CVPR, pages 4700- 4708, 2017.","title":"Densely connected convolutional networks","authors":"Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q Weinberger","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Krizhevsky et al., 2009] Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny im- ages. Technical report, Citeseer, 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lakshminarayanan et al., 2017] Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. Simple and scal- able predictive uncertainty estimation using deep ensem- bles. In NeurIPS, pages 6402-6413, 2017.","title":"Simple and scalable predictive uncertainty estimation using deep ensembles","authors":"Alexander Balaji Lakshminarayanan, Charles Pritzel, Blundell","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lan and Harvey, 2005] Yuxuan Lan and Richard Harvey. Image classification using compression distance. In Pro- ceedings of the 2nd International Conference on Vision, Video and Graphics, pages 173-180, 2005.","title":"Image classification using compression distance","authors":"Lan, Harvey ;, Yuxuan Lan, Richard Harvey","year":"2005","venue":"Proceedings of the 2nd International Conference on Vision, Video and Graphics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lee et al., 2018a] Kimin Lee, Honglak Lee, Kibok Lee, and Jinwoo Shin. Training confidence-calibrated classifiers for detecting out-of-distribution samples. In ICLR, 2018.","title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","authors":"Lee","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lee et al., 2018b] Kimin Lee, Kibok Lee, Honglak Lee, and Jinwoo Shin. A simple unified framework for detect- ing out-of-distribution samples and adversarial attacks. In NeurIPS, pages 7167-7177, 2018.","title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","authors":"Lee","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2004] Ming Li, Xin Chen, Xin Li, Bin Ma, and Paul MB Vitányi. The similarity metric. IEEE transactions on Information Theory, 50(12):3250-3264, 2004.","title":"The similarity metric","authors":"Ming Li, Xin Chen, Xin Li, Bin Ma, Paul Mb Vitányi","year":"2004","venue":"IEEE transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liang et al., 2008] Jan-Yie Liang, Chih-Sheng Chen, Chua- Huang Huang, and Li Liu. Lossless compression of med- ical images using hilbert space-filling curves. Comput- erized Medical Imaging and Graphics, 32(3):174-182, 2008.","title":"Lossless compression of medical images using hilbert space-filling curves","authors":"Jan-Yie Liang, Chih-Sheng Chen, Chua-Huang Huang, Li Liu","year":"2008","venue":"Computerized Medical Imaging and Graphics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liang et al., 2018] Shiyu Liang, Yixuan Li, and R. Srikant. Enhancing the reliability of out-of-distribution image de- tection in neural networks. In ICLR, 2018.","title":"Enhancing the reliability of out-of-distribution image detection in neural networks","authors":"Shiyu Liang, Yixuan Li, R Srikant","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lloyd, 1982] Stuart Lloyd. Least squares quantization in pcm. IEEE transactions on information theory, 28(2):129-137, 1982.","title":"Least squares quantization in pcm","authors":"Stuart Lloyd","year":"1982","venue":"IEEE transactions on information theory","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Malinin and Gales, 2018] Andrey Malinin and Mark Gales. Predictive uncertainty estimation via prior networks. In NeurIPS, pages 7047-7058, 2018.","title":"Predictive uncertainty estimation via prior networks","authors":"Andrey Malinin, Mark Gales","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Max, 1960] Joel Max. Quantizing for minimum distortion. IRE Transactions on Information Theory, 6(1):7-12, 1960.","title":"Quantizing for minimum distortion","authors":"Max ;, Joel Max","year":"1960","venue":"IRE Transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mortensen et al., 2009] Jonathan Mortensen, Jia Jie Wu, Ja- cob Furst, John Rogers, and Daniela Raicu. Effect of im- age linearization on normalized compression distance. In SPPR, pages 106-116, 2009.","title":"Effect of image linearization on normalized compression distance","authors":"Jonathan Mortensen, Jia Jie Wu, Jacob Furst, John Rogers, Daniela Raicu","year":"2009","venue":"SPPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Netzer et al., 2011] Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. Reading digits in natural images with unsupervised feature learn- ing. In NeurIPS Workshop, 2011.","title":"Reading digits in natural images with unsupervised feature learning","authors":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y Ng","year":"2011","venue":"NeurIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pinho and Ferreira, 2011] Armando J Pinho and Paulo JSG Ferreira. Image similarity using the normalized compres- sion distance based on finite context models. In ICIP, pages 1993-1996, 2011.","title":"Image similarity using the normalized compression distance based on finite context models","authors":"J Armando, Paulo Jsg Pinho, Ferreira","year":"2011","venue":"ICIP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Spracklin and Saxton, 2007] LM Spracklin and Lawrence V Saxton. Filtering spam using kolmogorov complexity estimates. In AINAW, volume 1, pages 321-328. IEEE, 2007.","title":"Filtering spam using kolmogorov complexity estimates","authors":"Saxton ; Lm Spracklin, Lawrence V Spracklin, Saxton","year":"2007","venue":"AINAW","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Vyas et al., 2018] Apoorv Vyas, Nataraj Jammalamadaka, Xia Zhu, Dipankar Das, Bharat Kaul, and Theodore L Willke. Out-of-distribution detection using an ensemble of self supervised leave-out classifiers. In ECCV, pages 550-564, 2018.","title":"Out-of-distribution detection using an ensemble of self supervised leave-out classifiers","authors":"Apoorv Vyas, Nataraj Jammalamadaka, Xia Zhu, Dipankar Das, Bharat Kaul, Theodore L Willke","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Welch, 1984] Terry A. Welch. Technique for high- performance data compression. Computer, (52), 1984.","title":"Technique for highperformance data compression","authors":"Terry A Welch","year":"1984","venue":"Computer","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2015] Pingmei Xu, Krista A Ehinger, Yinda Zhang, Adam Finkelstein, Sanjeev R Kulkarni, and Jianx- iong Xiao. Turkergaze: Crowdsourcing saliency with web- cam based eye tracking. arXiv preprint arXiv:1504.06755, 2015.","title":"Turkergaze: Crowdsourcing saliency with webcam based eye tracking","authors":"Xu","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yu et al., 2015] Fisher Yu, Ari Seff, Yinda Zhang, Shu- ran 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.","title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","authors":"Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, Jianxiong Xiao","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}