{"type":"ScholarlyArticle","title":"Redundancy-resistant Generative Hashing for Image Retrieval","authors":[{"name":"Changying Du","slug":"changying-du","given":"Changying","family":"Du","affiliation":"360 Search Lab , Beijing 100015 , China"},{"name":"Xingyu Xie","slug":"xingyu-xie","given":"Xingyu","family":"Xie","affiliation":"College of Automation , Nanjing University of Aeronautics and Astronautics , Nanjing , China"},{"name":"Changde Du","slug":"changde-du","given":"Changde","family":"Du","affiliation":"Institute of Automation , Chinese Academy of Sciences , Beijing 100190 , China"},{"name":"Hao Wang","slug":"hao-wang","given":"Hao","family":"Wang","affiliation":"360 Search Lab , Beijing 100015 , China"}],"abstract":"By optimizing probability distributions over discrete latent codes, Stochastic Generative Hashing (SGH) bypasses the critical and intractable binary constraints on hash codes. While encouraging results were reported, SGH still suffers from the deficient usage of latent codes, i.e., there often exist many uninformative latent dimensions in the code space, a disadvantage inherited from its auto-encoding variational framework. Motivated by the fact that code redundancy usually is severer when more complex decoder network is used, in this paper, we propose a constrained deep generative architecture to simplify the decoder for data reconstruction. Specifically, our new framework forces the latent hashing codes to not only reconstruct data through the generative network but also retain minimal squared L2 difference to the last real-valued network hidden layer. Furthermore, during posterior inference, we propose to regularize the standard auto-encoding objective with an additional term that explicitly accounts for the negative redundancy degree of latent code dimensions. We interpret such modifications as Bayesian posterior regularization and design an adversarial strategy to optimize the generative, the variational, and the redundancy-resistanting parameters. Empirical results show that our new method can significantly boost the quality of learned codes and achieve state-of-the-art performance for image retrieval.","doi":"10.24963/ijcai.2018/696","url":"https://ijcai.org/proceedings/2018/696","pdf":"https://ijcai.org/proceedings/2018/0696.pdf","markdown":"https://ijcai.org/proceedings/2018/696.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/696","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Uncertainty in AI","track":"Main track","number":696,"pages":{"first":5017,"last":5023},"keywords":["Machine Learning: Deep Learning","Machine Learning: Unsupervised Learning","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Machine Learning: Learning Generative Models","Computer Vision: Statistical Methods and Machine Learning","Uncertainty in AI: Approximate Probabilistic Inference"],"videos":[],"references":[{"position":1,"raw":"[Bowman et al., 2015] Samuel R Bowman, Luke Vilnis, O- riol Vinyals, Andrew M Dai, Rafal Jozefowicz, and Samy Bengio. Generating sentences from a continuous space. arXiv preprint arXiv:1511.06349, 2015.","title":"Generating sentences from a continuous space","authors":"Bowman","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Carreira-Perpinán and Raziperchikolaei, 2015] Miguel A Carreira-Perpinán and Ramin Raziperchikolaei. Hashing with binary autoencoders. In CVPR, 2015.","title":"Hashing with binary autoencoders","authors":"Ramin Miguel A Carreira-Perpinán, Raziperchikolaei","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2016] Xi Chen, Diederik P Kingma, Tim Sali- mans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskever, and Pieter Abbeel. Variational lossy autoen- coder. arXiv preprint arXiv:1611.02731, 2016.","title":"Variational lossy autoencoder","authors":"Xi Chen, P Diederik, Tim Kingma, Yan Salimans, Prafulla Duan, John Dhariwal, Ilya Schulman, Pieter Sutskever, Abbeel","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dai et al., 2017] Bo Dai, Ruiqi Guo, Sanjiv Kumar, Niao He, and Le Song. Stochastic generative hashing. In ICML, 2017.","title":"Stochastic generative hashing","authors":"Bo Dai, Ruiqi Guo, Sanjiv Kumar, Niao He, Le Song","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Erin Liong et al., 2015] Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, and Jie Zhou. Deep hashing for compact binary codes learning. In CVPR, 2015.","title":"Deep hashing for compact binary codes learning","authors":"Erin Liong","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gong et al., 2013] Yunchao Gong, Svetlana Lazebnik, Al- bert Gordo, and Florent Perronnin. Iterative quantiza- tion: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE Transactions on PAMI, 35(12):2916-2929, 2013.","title":"Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval","authors":"Gong","year":"2013","venue":"IEEE Transactions on PAMI","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Griffin et al., 2007] G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology, 2007.","title":"Caltech-256 object category dataset","authors":"G Griffin, A Holub, P Perona","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2013] Kaiming He, Fang Wen, and Jian Sun. K-means hashing: An affinity-preserving quantization method for learning binary compact codes. In CVPR, 2013.","title":"K-means hashing: An affinity-preserving quantization method for learning binary compact codes","authors":"Kaiming He, Fang Wen, Jian Sun","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Heo et al., 2015] Jae-Pil Heo, Youngwoon Lee, Junfeng He, Shih-Fu Chang, and Sung-Eui Yoon. Spherical hashing: Binary code embedding with hyperspheres. IEEE Trans- actions on PAMI, 37(11):2304-2316, 2015.","title":"Spherical hashing: Binary code embedding with hyperspheres","authors":"Jae-Pil Heo, Youngwoon Lee, Junfeng He, Shih-Fu Chang, Sung-Eui Yoon","year":"2015","venue":"IEEE Transactions on PAMI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hoffman, 2017] Matthew D Hoffman. Learning deep latent gaussian models with markov chain monte carlo. In ICML, 2017.","title":"Learning deep latent gaussian models with markov chain monte carlo","authors":"Matthew D Hoffman","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jiang and Li, 2015] Qing-Yuan Jiang and Wu-Jun Li. Scal- able graph hashing with feature transformation. In IJCAI, 2015.","title":"Scalable graph hashing with feature transformation","authors":"Li ; Qing-Yuan Jiang, Wu-Jun Jiang, Li","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/318"},{"position":12,"raw":"[Jiang and Li, 2016] Qing-Yuan Jiang and Wu-Jun Li. Deep cross-modal hashing. arXiv preprint arXiv:1602.02255, 2016.","title":"Deep cross-modal hashing","authors":"Li ; Qing-Yuan Jiang, Wu-Jun Jiang, Li","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kingma and Welling, 2014] Diederik P Kingma and Max Welling. Auto-encoding variational bayes. In ICLR, 2014.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kong and Li, 2012] Weihao Kong and Wu-Jun Li. Isotropic hashing. In NIPS, 2012.","title":"Weihao Kong and Wu-Jun Li. Isotropic hashing","authors":"Li Kong","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Krizhevsky, 2009] Alex Krizhevsky. Learning multiple lay- ers of features from tiny images. Technical report, Univ. of Toronto, 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lin et al., 2016] Kevin Lin, Jiwen Lu, Chu-Song Chen, and Jie Zhou. Learning compact binary descriptors with unsu- pervised deep neural networks. In CVPR, 2016.","title":"Learning compact binary descriptors with unsupervised deep neural networks","authors":"Kevin Lin, Jiwen Lu, Chu-Song Chen, Jie Zhou","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2014] Wei Liu, Cun Mu, Sanjiv Kumar, and Shih- Fu Chang. Discrete graph hashing. In NIPS, 2014.","title":"Discrete graph hashing","authors":"Wei Liu, Cun Mu, Sanjiv Kumar, Shih-Fu Chang","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lu et al., 2012] Can-Yi Lu, Hai Min, Zhong-Qiu Zhao, Lin Zhu, De-Shuang Huang, and Shuicheng Yan. Robust and efficient subspace segmentation via least squares regres- sion. ECCV, pages 347-360, 2012.","title":"Robust and efficient subspace segmentation via least squares regression","authors":"Lu","year":"2012","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Oliva and Torralba, 2001] Aude Oliva and Antonio Torral- ba. Modeling the shape of the scene: A holistic represen- tation of the spatial envelope. IJCV, 42(3):145-175, 2001.","title":"Aude Oliva and Antonio Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope","authors":"Torralba Oliva","year":"2001","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rezende et al., 2014] Danilo Jimenez Rezende, Shakir Mo- hamed, and Daan Wierstra. Stochastic backpropagation and approximate inference in deep generative models. In ICML, 2014.","title":"Stochastic backpropagation and approximate inference in deep generative models","authors":"Danilo Jimenez Rezende, Shakir Mohamed, Daan Wierstra","year":"2014","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Russakovsky et al., 2015] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. Imagenet large scale visual recognition challenge. IJCV, 115(3):211-252, 2015.","title":"Imagenet large scale visual recognition challenge","authors":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein","year":"2015","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sønderby et al., 2016] Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe, Søren Kaae Sønderby, and Ole Winther. Ladder variational autoencoders. In NIPS, 2016.","title":"Ladder variational autoencoders","authors":"Tapani Casper Kaae Sønderby, Lars Raiko, Søren Maaløe, Ole Kaae Sønderby, Winther","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Szegedy et al., 2015] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabi- novich. Going deeper with convolutions. In CVPR, 2015.","title":"Going deeper with convolutions","authors":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tomczak and Welling, 2017] Jakub M Tomczak and Max Welling. Vae with a vampprior. arXiv preprint arX- iv:1705.07120, 2017.","title":"Vae with a vampprior","authors":"M Jakub, Max Tomczak, Welling","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2012] Jun Wang, Sanjiv Kumar, and Shih Fu Chang. Semi-supervised hashing for large-scale search. IEEE Transactions on PAMI, 34(12):2393-2406, 2012.","title":"Semi-supervised hashing for large-scale search","authors":"Jun Wang, Sanjiv Kumar, Shih Fu, Chang","year":"2012","venue":"IEEE Transactions on PAMI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2017] Jingdong Wang, Ting Zhang, Nicu Sebe, Heng Tao Shen, et al. A survey on learning to hash. IEEE Transactions on PAMI, 2017.","title":"A survey on learning to hash","authors":"Jingdong Wang, Ting Zhang, Nicu Sebe, Heng Tao Shen","year":"2017","venue":"IEEE Transactions on PAMI","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Weiss et al., 2008] Yair Weiss, Antonio Torralba, and Rob Fergus. Spectral hashing. In NIPS, 2008.","title":"Spectral hashing","authors":"Yair Weiss, Antonio Torralba, Rob Fergus","year":"2008","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xia et al., 2014] Rongkai Xia, Yan Pan, Hanjiang Lai, Cong Liu, and Shuicheng Yan. Supervised hashing for image retrieval via image representation learning. In AAAI, 2014.","title":"Supervised hashing for image retrieval via image representation learning","authors":"Rongkai Xia, Yan Pan, Hanjiang Lai, Cong Liu, Shuicheng Yan","year":"2014","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yang et al., 2017] Zichao Yang, Zhiting Hu, Ruslan Salakhutdinov, and Taylor Berg-Kirkpatrick. Improved variational autoencoders for text modeling using dilated convolutions. In ICML, 2017.","title":"Improved variational autoencoders for text modeling using dilated convolutions","authors":"Yang","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yeung et al., 2017] Serena Yeung, Anitha Kannan, Yann Dauphin, and Li Fei-Fei. Tackling over-pruning in vari- ational autoencoders. arXiv preprint arXiv:1706.03643, 2017.","title":"Tackling over-pruning in variational autoencoders","authors":"Serena Yeung, Anitha Kannan, Yann Dauphin, Li Fei-Fei","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhu et al., 2014] Jun Zhu, Ning Chen, and Eric P Xing. Bayesian inference with posterior regularization and appli- cations to infinite latent SVMs. JMLR, 15(1):1799-1847, 2014.","title":"Bayesian inference with posterior regularization and applications to infinite latent SVMs","authors":"Jun Zhu, Ning Chen, Eric P Xing","year":"2014","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu et al., 2016] Han Zhu, Mingsheng Long, Jianmin Wang, and Yue Cao. Deep hashing network for efficient similarity retrieval. In AAAI, 2016.","title":"Deep hashing network for efficient similarity retrieval","authors":"Han Zhu, Mingsheng Long, Jianmin Wang, Yue Cao","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}