{"type":"ScholarlyArticle","title":"Open Category Classification by Adversarial Sample Generation","authors":[{"name":"Yang Yu","slug":"yang-yu","given":"Yang","family":"Yu","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China; Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing , China"},{"name":"Wei-Yang Qu","slug":"wei-yang-qu","given":"Wei-Yang","family":"Qu","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing , China; Collaborative Innovation Center of Novel Software Technology and Industrialization , Nanjing , China"},{"name":"Nan Li","slug":"nan-li","given":"Nan","family":"Li","affiliation":"Alibaba Group , Hangzhou , China"},{"name":"Zimin Guo","slug":"zimin-guo","given":"Zimin","family":"Guo","affiliation":"College of Engineering , UC Berkeley"}],"abstract":"In real-world classification tasks, it is difficult to collect training samples from all possible categories of the environment. Therefore, when an instance of an unseen class appears in the prediction stage, a robust classifier should be able to tell that it is from an unseen class, instead of classifying it to be any known category. In this paper, adopting the idea of adversarial learning, we propose the ASG framework for open-category classification. ASG generates positive and negative samples of seen categories in the unsupervised manner via an adversarial learning strategy. With the generated samples, ASG then learns to tell seen from unseen in the supervised manner. Experiments performed on several datasets show the effectiveness of ASG.","doi":"10.24963/ijcai.2017/469","url":"https://ijcai.org/proceedings/2017/469","pdf":"https://ijcai.org/proceedings/2017/0469.pdf","markdown":"https://ijcai.org/proceedings/2017/469.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/469","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":469,"pages":{"first":3357,"last":3363},"keywords":["Machine Learning: Classification","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Bendale and Boult, 2015] Abhijit Bendale and Terrance E. Boult. Towards open world recognition. In CVPR'15, pages 1893-1902, Boston, MA, 2015.","title":"Towards open world recognition","authors":"Abhijit Bendale, Terrance E Boult","year":"2015","venue":"CVPR'15","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brochu et al., 2010] Eric Brochu, Vlad M. Cora, and Nando de Freitas. A tutorial on bayesian optimization of ex- pensive cost functions, with application to active user modeling and hierarchical reinforcement learning. CoRR, abs/1012.2599, 2010.","title":"A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","authors":"Eric Brochu, Vlad M Cora, Nando De Freitas","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang and Lin, 2011] C.C. Chang and C.J. Lin. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3):27, 2011.","title":"LIBSVM: A library for support vector machines","authors":"C C Chang, C J Lin","year":"2011","venue":"ACM Transactions on Intelligent Systems and Technology","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chow, 1970] C Chow. On optimum recognition error and reject tradeoff. IEEE Transactions on Information Theory, 16(1):41-46, 1970.","title":"On optimum recognition error and reject tradeoff","authors":"Chow","year":"1970","venue":"IEEE Transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Da et al., 2014] Qing Da, Yang Yu, and Zhi-Hua Zhou. Learning with augmented class by exploiting unlabeled data. In AAAI'14, pages 1760-1766, Quebec, Canada, 2014.","title":"Learning with augmented class by exploiting unlabeled data","authors":"Qing Da, Yang Yu, Zhi-Hua Zhou","year":"2014","venue":"AAAI'14","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fink et al., 2006] Michael Fink, Shai Shalev-Shwartz, Yoram Singer, and Shimon Ullman. Online multiclass learning by interclass hypothesis sharing. In ICML'06, pages 313-320, Pittsburgh, PA, 2006.","title":"Online multiclass learning by interclass hypothesis sharing","authors":"Michael Fink, Shai Shalev-Shwartz, Yoram Singer, Shimon Ullman","year":"2006","venue":"ICML'06","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Goldberg, 1989] David E. Goldberg. Genetic Algorithms in Search Optimization and Machine Learning. Addison- Wesley, 1989.","title":"Genetic Algorithms in Search Optimization and Machine Learning","authors":"David E Goldberg","year":"1989","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Goodfellow et al., 2014] I.J. Goodfellow, Jean P.A., Mehdi Mirza, Bing Xu, W. F. David, Sherjil Ozair, Courville A. C., and Yoshua Bengio. Generative adversarial nets. In Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger, editors, NIPS 27, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Goodfellow","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hodge and Austin, 2004] Victoria J Hodge and Jim Austin. A survey of outlier detection methodologies. Artificial In- telligence Review, 22(2):85-126, 2004.","title":"A survey of outlier detection methodologies","authors":"J Victoria, Jim Hodge, Austin","year":"2004","venue":"Artificial Intelligence Review","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hospedales et al., 2013] Timothy M Hospedales, Shaogang Gong, and Tao Xiang. Finding rare classes: Ac- tive learning with generative and discriminative models. IEEE Transactions on Knowledge and Data Engineering, 25(2):374-386, 2013.","title":"Finding rare classes: Active learning with generative and discriminative models","authors":"Timothy M Hospedales, Shaogang Gong, Tao Xiang","year":"2013","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kuzborskij et al., 2013] I. Kuzborskij, F. Orabona, and B. Caputo. From N to N+1: Multiclass transfer incremen- tal learning. In CVPR'13, pages 3358-3365, Portland, OR, 2013.","title":"From N to N+1: Multiclass transfer incremental learning","authors":"Kuzborskij","year":"2013","venue":"CVPR'13","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2016] Wei Li, Melvin Gauci, and Roderich Gro. Turing learning: a metric-free approach to inferring be- havior and its application to swarms. Swarm Intelligence, 10(3):211-243, 2016.","title":"Turing learning: a metric-free approach to inferring behavior and its application to swarms","authors":"Wei Li, Melvin Gauci, Roderich Gro","year":"2016","venue":"Swarm Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ma and Perkins, 2003] Junshui Ma and Simon Perkins. Time-series novelty detection using one-class support vec- tor machines. In IJCNN'03, volume 3, pages 1741-1745, 2003.","title":"Junshui Ma and Simon Perkins. Time-series novelty detection using one-class support vector machines","authors":"Perkins Ma","year":"2003","venue":"IJCNN'03","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Muhlbaier et al., 2009] M.D. Muhlbaier, A. Topalis, and R. Polikar. Learn++ NC: Combining ensemble of clas- sifiers with dynamically weighted consult-and-vote for ef- ficient incremental learning of new classes. IEEE Trans- actions on Neural Networks, 20(1):152-168, 2009.","title":"Learn++ NC: Combining ensemble of classifiers with dynamically weighted consult-and-vote for efficient incremental learning of new classes","authors":"M D Muhlbaier, A Topalis, R Polikar","year":"2009","venue":"IEEE Transactions on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Munos, 2014] Rémi Munos. From bandits to monte-carlo tree search: The optimistic principle applied to optimiza- tion and planning. Foundations and Trends in Machine Learning, 7(1):1-129, 2014.","title":"From bandits to monte-carlo tree search: The optimistic principle applied to optimization and planning","authors":"Rémi Munos, Munos","year":"2014","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nowozin et al., 2016] Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. f-gan: Training generative neural samplers using variational divergence minimization. In Daniel D. Lee, Masashi Sugiyama, Ulrike V. Luxburg, Is- abelle Guyon, and Roman Garnett, editors, NIPS 29, pages 271-279, 2016.","title":"f-gan: Training generative neural samplers using variational divergence minimization","authors":"Sebastian Nowozin, Botond Cseke, Ryota Tomioka","year":"2016","venue":"NIPS 29","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Palatucci et al., 2009] Mark Palatucci, Dean Pomerleau, Geoffrey E. Hinton, and Tom M. Mitchell. Zero-shot learning with semantic output codes. In Yoshua Ben- gio, Dale Schuurmans, John D. Lafferty, Christopher K. I. Williams, and Aron Culotta, editors, NIPS 22, pages 1410-1418, 2009.","title":"Zero-shot learning with semantic output codes","authors":"Mark Palatucci, Dean Pomerleau, Geoffrey E Hinton, Tom M Mitchell","year":"2009","venue":"NIPS 22","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pelleg and Moore, 2005] Dan Pelleg and Andrew W. Moore. Active learning for anomaly and rare-category detection. In L.K. Saul, Y. Weiss, and L. Bottou, editors, NIPS 17, pages 1073-1080. 2005.","title":"Active learning for anomaly and rare-category detection","authors":"Dan Pelleg, Andrew W Moore","year":"2005","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Phillips et al., 2011] P Jonathon Phillips, Patrick Grother, and Ross Micheals. Evaluation methods in face recogni- tion. In Handbook of Face Recognition, pages 551-574. 2011.","title":"Evaluation methods in face recognition","authors":"Jonathon Phillips, Patrick Grother, Ross Micheals","year":"2011","venue":"Handbook of Face Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rifkin and Klautau, 2004] Ryan Rifkin and Aldebaro Klau- tau. In defense of one-vs-all classification. Journal of Ma- chine Learning Research, 5:101-141, 2004.","title":"In defense of one-vs-all classification","authors":"Ryan Rifkin, Aldebaro Klautau","year":"2004","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Scheirer et al., 2013] Walter J Scheirer, Terrance E Boult, Anderson de Rezende Rocha, and Archana Sapkota. To- ward open set recognition. IEEE Transactions on Pat- tern Analysis and Machine Intelligence, 35(7):1757-1772, 2013.","title":"Toward open set recognition","authors":"J Walter, Terrance E Scheirer, Anderson Boult, De Rezende, Archana Rocha, Sapkota","year":"2013","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"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":23,"raw":"[Xian et al., 2016] Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh N. Nguyen, Matthias Hein, and Bernt Schiele. Latent embeddings for zero-shot classification. In CVPR'16, pages 69-77, Las Vegas, NV, 2016.","title":"Latent embeddings for zero-shot classification","authors":"Xian","year":"2016","venue":"CVPR'16","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2016] Yang Yu, Hong Qian, and Yi-Qi Hu. Derivative-free optimization via classification. In AAAI'16, pages 2286-2292, Phoenix, AZ, 2016.","title":"Derivative-free optimization via classification","authors":"Yang Yu, Hong Qian, Yi-Qi Hu","year":"2016","venue":"AAAI'16","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhou and Chen, 2002] Zhi-Hua Zhou and Zhao-Qian Chen. Hybrid decision tree. Knowledge-based systems, 15(8):515-528, 2002.","title":"Hybrid decision tree","authors":"Chen ; ] Zhi-Hua Zhou, Zhao-Qian Zhou, Chen","year":"2002","venue":"Knowledge-based systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}