{"type":"ScholarlyArticle","title":"Constrained Adaptive Projection with Pretrained Features for Anomaly Detection","authors":[{"name":"Xingtai Gui","slug":"xingtai-gui","given":"Xingtai","family":"Gui","affiliation":"School of Automation Engineering , University of Electronic Science and Technology of China(UESTC)"},{"name":"Di Wu","slug":"di-wu","given":"Di","family":"Wu","affiliation":"School of Automation Engineering , University of Electronic Science and Technology of China(UESTC)"},{"name":"Yang Chang","slug":"yang-chang","given":"Yang","family":"Chang","affiliation":"School of Automation Engineering , University of Electronic Science and Technology of China(UESTC); Shenzhen Institute for Advanced Study , UESTC"},{"name":"Shicai Fan","slug":"shicai-fan","given":"Shicai","family":"Fan","affiliation":"School of Automation Engineering , University of Electronic Science and Technology of China(UESTC); Shenzhen Institute for Advanced Study , UESTC"}],"abstract":"Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning on one-class training data. In this paper, we propose an anomaly detection framework called constrained adaptive projection with pretrained features (CAP). Combined with pretrained features, a simple linear projection head applied on a specific input and its k most similar pretrained normal representations is designed for feature adaptation, and a reformed self-attention is leveraged to mine the inner-relationship among one-class semantic features. A loss function is proposed to avoid potential pattern collapse. Concretely, it considers the similarity between a specific data and its corresponding adaptive normal representation, and incorporates a constraint term slightly aligning pretrained and adaptive spaces. Our method achieves state-of-the-art anomaly detection performance on semantic anomaly detection and sensory anomaly detection benchmarks including 96.5% AUROC on CIFAR-100 dataset, 97.0% AUROC on CIFAR-10 dataset and 89.9% AUROC on MvTec dataset.","doi":"10.24963/ijcai.2022/286","url":"https://ijcai.org/proceedings/2022/286","pdf":"https://ijcai.org/proceedings/2022/0286.pdf","markdown":"https://ijcai.org/proceedings/2022/286.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/286","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":286,"pages":{"first":2059,"last":2065},"keywords":["Data Mining: Applications","Computer Vision: Applications","Data Mining: Anomaly/Outlier Detection"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986713","length_sec":85,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984856","length_sec":331,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Angiulli and Pizzuti, 2002] Fabrizio Angiulli and Clara Piz- zuti. Fast outlier detection in high dimensional spaces. In European conference on principles of data mining and knowledge discovery, pages 15-27. Springer, 2002.","title":"Fabrizio Angiulli and Clara Pizzuti. Fast outlier detection in high dimensional spaces","authors":"Pizzuti Angiulli","year":"2002","venue":"European conference on principles of data mining and knowledge discovery","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bergman et al., 2020] Liron Bergman, Niv Cohen, and Yedid Hoshen. Deep nearest neighbor anomaly detection. arXiv preprint arXiv:2002.10445, 2020.","title":"Deep nearest neighbor anomaly detection","authors":"Liron Bergman, Niv Cohen, Yedid Hoshen","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bergmann et al., 2020] Paul Bergmann, Michael Fauser, David Sattlegger, and Carsten Steger. Uninformed stu- dents: Student-teacher anomaly detection with discrimina- tive latent embeddings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4183-4192, 2020.","title":"Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings","authors":"Paul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2020] Ting Chen, Simon Kornblith, Moham- mad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations. In In- ternational conference on machine learning, pages 1597- 1607. PMLR, 2020.","title":"A simple framework for contrastive learning of visual representations","authors":"Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton","year":"2020","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ding and Kolaczyk, 2013] Qi Ding and Eric D Kolaczyk. A compressed pca subspace method for anomaly detection in high-dimensional data. IEEE Transactions on Information Theory, 59(11):7419-7433, 2013.","title":"A compressed pca subspace method for anomaly detection in high-dimensional data","authors":"Kolaczyk ; ] Qi Ding, Eric D Ding, Kolaczyk","year":"2013","venue":"IEEE Transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong et al., 2021] Jiahua Dong, Yang Cong, Gan Sun, Zhen Fang, and Zhengming Ding. Where and how to transfer: knowledge aggregation-induced transferability perception for unsupervised domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.","title":"Where and how to transfer: knowledge aggregation-induced transferability perception for unsupervised domain adaptation","authors":"Jiahua Dong, Yang Cong, Gan Sun, Zhen Fang, Zhengming Ding","year":"2021","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Glodek et al., 2013] Michael Glodek, Martin Schels, and Friedhelm Schwenker. Ensemble gaussian mixture models for probability density estimation. Computational statis- tics, 28(1):127-138, 2013.","title":"Ensemble gaussian mixture models for probability density estimation","authors":"Michael Glodek, Martin Schels, Friedhelm Schwenker","year":"2013","venue":"Computational statistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gong et al., 2019] Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel. Memorizing nor- mality to detect anomaly: Memory-augmented deep au- toencoder for unsupervised anomaly detection. In Pro- ceedings of the IEEE/CVF International Conference on Computer Vision, pages 1705-1714, 2019.","title":"Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection","authors":"Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, Anton Van Den, Hengel","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hendrycks et al., 2019] Dan Hendrycks, Mantas Mazeika, Saurav Kadavath, and Dawn Song. Using self-supervised learning can improve model robustness and uncertainty. arXiv preprint arXiv:1906.12340, 2019.","title":"Using self-supervised learning can improve model robustness and uncertainty","authors":"Dan Hendrycks, Mantas Mazeika, Saurav Kadavath, Dawn Song","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Perera et al., 2019] Pramuditha Perera, Ramesh Nallapati, and Bing Xiang. Ocgan: One-class novelty detection using gans with constrained latent representations. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2898-2906, 2019.","title":"Ocgan: One-class novelty detection using gans with constrained latent representations","authors":"Perera","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Reiss et al., 2021] Tal Reiss, Niv Cohen, Liron Bergman, and Yedid Hoshen. Panda: Adapting pretrained features for anomaly detection and segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 2806-2814, 2021.","title":"Panda: Adapting pretrained features for anomaly detection and segmentation","authors":"Reiss","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ruff et al., 2018] Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexan- der Binder, Emmanuel Müller, and Marius Kloft. Deep one-class classification. In International conference on machine learning, pages 4393-4402. PMLR, 2018.","title":"Deep one-class classification","authors":"Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Ahmed Shoaib, Alexander Siddiqui, Emmanuel Binder, Marius Müller, Kloft","year":"2018","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ruff et al., 2019] Lukas Ruff, Robert A Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller, and Marius Kloft. Deep semi-supervised anomaly detection. arXiv preprint arXiv:1906.02694, 2019.","title":"Deep semi-supervised anomaly detection","authors":"Lukas Ruff, Robert A Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller, Marius Kloft","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ruff et al., 2021] Lukas Ruff, Jacob R Kauffmann, Robert A Vandermeulen, Grégoire Montavon, Wojciech Samek, Marius Kloft, Thomas G Dietterich, and Klaus- Robert Müller. A unifying review of deep and shallow anomaly detection. Proceedings of the IEEE, 2021.","title":"A unifying review of deep and shallow anomaly detection","authors":"Lukas Ruff, Robert A Jacob R Kauffmann, Grégoire Vandermeulen, Wojciech Montavon, Marius Samek, Thomas G Kloft, Klaus-Robert Dietterich, Müller","year":"2021","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Salehi et al., 2021] Mohammadreza Salehi, Niousha Sad- jadi, Soroosh Baselizadeh, Mohammad H Rohban, and Hamid R Rabiee. Multiresolution knowledge distillation for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14902-14912, 2021.","title":"Multiresolution knowledge distillation for anomaly detection","authors":"Mohammadreza Salehi, Niousha Sadjadi, Soroosh Baselizadeh, Mohammad H Rohban, Hamid R Rabiee","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Schölkopf et al., 2001] Bernhard Schölkopf, John C Platt, John Shawe-Taylor, Alex J Smola, and Robert C Williamson. Estimating the support of a high-dimensional distribution. Neural computation, 13(7):1443-1471, 2001.","title":"Estimating the support of a high-dimensional distribution","authors":"Bernhard Schölkopf, John C Platt, John Shawe-Taylor, Alex J Smola, Robert C Williamson","year":"2001","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Su et al., 2019] Yanzhou Su, Yongjian Wu, Min Wang, Feng Wang, and Jian Cheng. Semantic segmentation of high resolution remote sensing image based on batch- attention mechanism. In IGARSS 2019-2019 IEEE In- ternational Geoscience and Remote Sensing Symposium, pages 3856-3859. IEEE, 2019.","title":"Semantic segmentation of high resolution remote sensing image based on batchattention mechanism","authors":"Yanzhou Su, Yongjian Wu, Min Wang, Feng Wang, Jian Cheng","year":"2019","venue":"IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tolstikhin et al., 2021] Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Peter Steiner, Daniel Keysers, Jakob Uszkoreit, et al. Mlp-mixer: An all-mlp architecture for vision. In Thirty-Fifth Conference on Neural Information Processing Systems, 2021.","title":"Mlp-mixer: An all-mlp architecture for vision","authors":"Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Peter Steiner, Daniel Keysers, Jakob Uszkoreit","year":"2021","venue":"Thirty-Fifth Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in neural information processing sys- tems, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yang et al., 2021] Jingkang Yang, Kaiyang Zhou, Yixuan Li, and Ziwei Liu. Generalized out-of-distribution detec- tion: A survey. arXiv preprint arXiv:2110.11334, 2021.","title":"Generalized out-of-distribution detection: A survey","authors":"Yang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhou et al., 2016] Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceed- ings of the IEEE conference on computer vision and pat- tern recognition, pages 2921-2929, 2016.","title":"Learning deep features for discriminative localization","authors":"Zhou","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}