Classification-Reconstruction Learning for Open-Set Recognition

Open-set classification is a problem of handling ‘unknown’ classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns. In contrast, we train networks for joint classification and reconstruction of input data. This enhances the learned representation so as to preserve information useful for separating unknowns from knowns, as well as to discriminate classes of knowns. Our novel Classification-Reconstruction learning for Open-Set Recognition (CROSR) utilizes latent representations for reconstruction and enables robust unknown detection without harming the known-class classification accuracy. Extensive experiments reveal that the proposed method outperforms existing deep open-set classifiers in multiple standard datasets and is robust to diverse outliers.

[1]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Georg Langs,et al.  Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery , 2017, IPMI.

[3]  Harri Valpola,et al.  From neural PCA to deep unsupervised learning , 2014, ArXiv.

[4]  Hans-Peter Kriegel,et al.  A survey on unsupervised outlier detection in high‐dimensional numerical data , 2012, Stat. Anal. Data Min..

[5]  Anderson Rocha,et al.  Toward Open Set Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Weng-Keen Wong,et al.  Open Set Learning with Counterfactual Images , 2018, ECCV.

[8]  Mario Lucic,et al.  Are GANs Created Equal? A Large-Scale Study , 2017, NeurIPS.

[9]  Randy C. Paffenroth,et al.  Anomaly Detection with Robust Deep Autoencoders , 2017, KDD.

[10]  Bo Zong,et al.  Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection , 2018, ICLR.

[11]  Mengjie Zhang,et al.  Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation , 2016, ECCV.

[12]  Vishal M. Patel,et al.  Sparse Representation-Based Open Set Recognition , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[14]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[15]  Terrance E. Boult,et al.  Towards Open Set Deep Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Francesco Cricri,et al.  Clustering and Unsupervised Anomaly Detection with l2 Normalized Deep Auto-Encoder Representations , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[17]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[18]  R. Srikant,et al.  Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.

[19]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[20]  Lei Shu,et al.  DOC: Deep Open Classification of Text Documents , 2017, EMNLP.

[21]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[22]  Stephen J. Roberts,et al.  A Probabilistic Resource Allocating Network for Novelty Detection , 1994, Neural Computation.

[23]  Jennifer Rexford,et al.  Sensitivity of PCA for traffic anomaly detection , 2007, SIGMETRICS '07.

[24]  Luca Maria Gambardella,et al.  Deep, Big, Simple Neural Nets for Handwritten Digit Recognition , 2010, Neural Computation.

[25]  Bing Liu,et al.  Breaking the Closed World Assumption in Text Classification , 2016, NAACL.

[26]  Tao Mei,et al.  Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[27]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[28]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[29]  Rahil Garnavi,et al.  Generative OpenMax for Multi-Class Open Set Classification , 2017, BMVC.

[30]  Vishal M. Patel,et al.  Learning Deep Features for One-Class Classification , 2018, IEEE Transactions on Image Processing.

[31]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[32]  Kenta Oono,et al.  Chainer : a Next-Generation Open Source Framework for Deep Learning , 2015 .

[33]  Anderson Rocha,et al.  Meta-Recognition: The Theory and Practice of Recognition Score Analysis , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[35]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[36]  Terrance E. Boult,et al.  Probability Models for Open Set Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[38]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[39]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[40]  Thomas Brox,et al.  Inverting Visual Representations with Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Nicu Sebe,et al.  Learning Deep Representations of Appearance and Motion for Anomalous Event Detection , 2015, BMVC.

[42]  Kibok Lee,et al.  Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification , 2016, ICML.

[43]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[44]  Lindley R. Higgins,et al.  Maintenance Engineering Handbook , 1967 .

[45]  Ole Winther,et al.  Auxiliary Deep Generative Models , 2016, ICML.

[46]  Ricardo da Silva Torres,et al.  Nearest neighbors distance ratio open-set classifier , 2016, Machine Learning.

[47]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[48]  Wolfram Burgard,et al.  The limits and potentials of deep learning for robotics , 2018, Int. J. Robotics Res..

[49]  Terrance E. Boult,et al.  Towards Open World Recognition , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Terrance E. Boult,et al.  The Extreme Value Machine , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[51]  Terrance E. Boult,et al.  Animal recognition in the Mojave Desert: Vision tools for field biologists , 2013, 2013 IEEE Workshop on Applications of Computer Vision (WACV).

[52]  Yoshua Bengio,et al.  Deconstructing the Ladder Network Architecture , 2015, ICML.

[53]  Lei Shu,et al.  Unseen Class Discovery in Open-world Classification , 2018, ArXiv.