{"type":"ScholarlyArticle","title":"Binarized Neural Networks for Resource-Efficient Hashing with Minimizing Quantization Loss","authors":[{"name":"Feng Zheng","slug":"feng-zheng","given":"Feng","family":"Zheng","affiliation":"Department of Computer Science and Engineering , Southern University of Science and Technology"},{"name":"Cheng Deng","slug":"cheng-deng","given":"Cheng","family":"Deng","affiliation":"School of Electronic Enigineering , Xidian University"},{"name":"Heng Huang","slug":"heng-huang","given":"Heng","family":"Huang","affiliation":"Department of Electrical and Computer Engineering , University of Pittsburgh; JD Finance America Corporation"}],"abstract":"In order to solve the problem of memory consumption and computational requirements, this paper proposes a novel learning binary neural network framework to achieve a resource-efficient deep hashing. In contrast to floating-point (32-bit) full-precision networks, the proposed method achieves a 32x model compression rate. At the same time, computational burden in convolution is greatly reduced due to efficient Boolean operations. To this end, in our framework, a new quantization loss defined between the binary weights and the learned real values is minimized to reduce the model distortion, while, by minimizing a binary entropy function, the discrete optimization is successfully avoided and the stochastic gradient descend method can be used smoothly. More importantly, we provide two theories to demonstrate the necessity and effectiveness of minimizing the quantization losses for both weights and activations. Numerous experiments show that the proposed method can achieve fast code generation without sacrificing accuracy.","doi":"10.24963/ijcai.2019/145","url":"https://ijcai.org/proceedings/2019/145","pdf":"https://ijcai.org/proceedings/2019/0145.pdf","markdown":"https://ijcai.org/proceedings/2019/145.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/145","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Computer Vision","track":"Main track","number":145,"pages":{"first":1032,"last":1040},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Computer Vision: Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Courbariaux and Bengio, 2015] Matthieu Courbariaux and Yoshua Bengio. Binaryconnect: Training deep neural net- works with binary weights during propagations. In NIPS, pages 3123-3131, 2015.","title":"Binaryconnect: Training deep neural networks with binary weights during propagations","authors":"Bengio Courbariaux, Matthieu Courbariaux, Yoshua Bengio","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Courbariaux et al., 2016] Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Ben- gio. Binarized neural networks: Training neural networks with weights and activations constrained to +1 or 1. In NIPS, pages 4114-4122, 2016.","title":"Binarized neural networks: Training neural networks with weights and activations constrained to +1 or 1","authors":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Do et al., 2016] Thanh-Toan Do, Anh-Dzung Doan, and Ngai-Man Cheung. Learning to hash with binary deep neural network. In ECCV, pages 219-234, 2016.","title":"Learning to hash with binary deep neural network","authors":"Thanh-Toan Do, Anh-Dzung Doan, Ngai-Man Cheung","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Farenzena et al., 2010] Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, and Marco Cristani. Person re-identification by symmetry-driven accumulation of local features. In CVPR, pages 2360-2367, 2010.","title":"Person re-identification by symmetry-driven accumulation of local features","authors":"Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, Marco Cristani","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gong et al., 2013] Yunchao Gong, Svetlana Lazebnik, Al- bert Gordo, and Florent Perronnin. Iterative quantization: A procrustean approach to learning binary codes for large- scale image retrieval. IEEE TPAMI, 35(12):2916 -2929, 2013.","title":"Iterative quantization: A procrustean approach to learning binary codes for largescale image retrieval","authors":"Gong","year":"2013","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Han et al., 2015] Song Han, Jeff Pool, John Tran, and William J. Dally. Learning both weights and connections for efficient neural network. In NIPS, pages 1135-1143, 2015.","title":"Learning both weights and connections for efficient neural network","authors":"Han","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":7,"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 TPAMI, 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 TPAMI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hinton et al., 2015] Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. In arXiv preprint arXiv:1503.02531, 2015.","title":"Distilling the knowledge in a neural network","authors":"Geoffrey Hinton, Oriol Vinyals, Jeff Dean","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hou et al., 2017] Lu Hou, Quanming Yao, and James T. Kwok. Loss-aware binarization of deep networks. In ICLR, 2017.","title":"Loss-aware binarization of deep networks","authors":"Lu Hou, Quanming Yao, James T Kwok","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2016] Chen Huang, Chen Change Loy, and Xiaoou Tang. Unsupervised learning of discriminative at- tributes and visual representations. In CVPR, pages 5175- 5184, 2016.","title":"Unsupervised learning of discriminative attributes and visual representations","authors":"Chen Huang, Chen Change Loy, Xiaoou Tang","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Indyk and Motwani, 1998] Piotr Indyk and Rajeev Mot- wani. Approximate nearest neighbors: towards remov- ing the curse of dimensionality. In STOC, pages 604-613, 1998.","title":"Approximate nearest neighbors: towards removing the curse of dimensionality","authors":"Piotr Indyk, Rajeev Motwani","year":"1998","venue":"STOC","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krizhevsky and Hinton, 2009] Alex Krizhevsky and Geof- frey Hinton. Learning multiple layers of features from tiny images. Technical report, University of Toronto, 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":13,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1097- 1105, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lai et al., 2015] Hanjiang Lai, Yan Pan, Ye Liux, and Shuicheng Yan. Simultaneous feature learning and hash coding with deep neural networks. In CVPR, pages 3270- 3278, 2015.","title":"Simultaneous feature learning and hash coding with deep neural networks","authors":"Hanjiang Lai, Yan Pan, Ye Liux, Shuicheng Yan","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2016] Fengfu Li, Bo Zhang, and Bin Liu. Ternary weight networks. In Workshop in NIPS, 2016.","title":"Ternary weight networks","authors":"Li","year":"2016","venue":"Workshop in NIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liny et al., 2016] Kevin Liny, Jiwen Luz, Chu-Song Cheny, and Jie Zhou. Learning compact binary descriptors with unsupervised deep neural networks. In CVPR, pages 1183-1192, 2016.","title":"Learning compact binary descriptors with unsupervised deep neural networks","authors":"Kevin Liny, Jiwen Luz, Chu-Song Cheny, Jie Zhou","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[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, pages 2475- 2483, 2015.","title":"Deep hashing for compact binary codes learning","authors":"Liong","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2016a] Haomiao Liu, Ruiping Wang, Shiguang Shan, and Xilin Chen. Deep supervised hashing for fast image retrieval. In CVPR, pages 2064-2072, 2016.","title":"Deep supervised hashing for fast image retrieval","authors":"Liu","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2016b] Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. A deep learning-based approach to pro- gressive vehicle re-identification for urban surveillance. In ECCV, pages 869-884, 2016.","title":"A deep learning-based approach to progressive vehicle re-identification for urban surveillance","authors":"Liu","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Perpinan and Raziperchikolaei, 2015] Miguel A. Carreira Perpinan and Ramin Raziperchikolaei. Hashing with bi- nary autoencoders. In CVPR, pages 557-566, 2015.","title":"Hashing with binary autoencoders","authors":"Miguel A Carreira Perpinan, Ramin Raziperchikolaei","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rastegariy et al., 2016] Mohammad Rastegariy, Vicente Ordonezy, Joseph Redmon, and Ali Farhadi. Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV, pages 525-542, 2016.","title":"Xnor-net: Imagenet classification using binary convolutional neural networks","authors":"Mohammad Rastegariy, Vicente Ordonezy, Joseph Redmon, Ali Farhadi","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Schrof et al., 2015] Florian Schrof, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In CVPR, pages 815-823, 2015.","title":"Facenet: A unified embedding for face recognition and clustering","authors":"Florian Schrof, Dmitry Kalenichenko, James Philbin","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shen et al., 2015] Fumin Shen, Chunhua Shen, Wei Liu, and Heng Tao Shen. Supervised discrete hashing. In CVPR, pages 37-45, 2015.","title":"Supervised discrete hashing","authors":"Shen","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Szegedy et al., 2015] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Du- mitru Erhan Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. In CVPR, pages 1-9, 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":26,"raw":"[van de Weijer et al., 2007] Joost van de Weijer, Cordelia Schmid, Jakob Verbeek, and Diane Larlus. Learning color names for real-world applications. In CVPR, 2007.","title":"Learning color names for real-world applications","authors":"Van De Weijer","year":"2007","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Venkateswara et al., 2017] Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Pan- chanathan. Deep hashing network for unsupervised do- main adaptation. In CVPR, pages 5018-5027, 2017.","title":"Deep hashing network for unsupervised domain adaptation","authors":"Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, Sethuraman Panchanathan","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2012] Jun Wang, Sanjiv Kumar, and Shih-Fu Chang. Semi-supervised hashing for large-scale search. IEEE TPAMI, 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 TPAMI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Weiss et al., 2009] Yair Weiss, Torralba, and Rob Fergus. Spectral hashing. In NIPS, pages 1753-1760, 2009.","title":"Spectral hashing","authors":"Yair Weiss, Rob Torralba, Fergus","year":"2009","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yan et al., 2007] Shuicheng Yan, Dong Xu, Benyu Zhang, Hong jiang Zhang, Qiang Yang, and Stephen Lin. Graph embedding and extensions: A general framework for di- mensionality reduction. IEEE TPAMI, 29(1), 2007.","title":"Graph embedding and extensions: A general framework for dimensionality reduction","authors":"Shuicheng Yan, Dong Xu, Benyu Zhang, Hong Jiang Zhang, Qiang Yang, Stephen Lin","year":"2007","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhao et al., 2013a] Rui Zhao, Wanli Ouyang, and Xiaogang Wang. Person re-identification by salience matching. In ICCV, pages 2528-2535, 2013.","title":"Person re-identification by salience matching","authors":"Zhao","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhao et al., 2013b] Rui Zhao, Wanli Ouyang, and Xiaogang Wang. Unsupervised salience learning for person re- identification. In CVPR, pages 3586-3593, 2013.","title":"Unsupervised salience learning for person reidentification","authors":"Zhao","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhao et al., 2014] Rui Zhao, Wanli Ouyang, and Xiao- gang Wang. Learning mid-level filters for person re- identification. In Proc. CVPR, pages 144-151, 2014.","title":"Learning mid-level filters for person reidentification","authors":"Rui Zhao, Wanli Ouyang, Xiaogang Wang","year":"2014","venue":"Proc. CVPR","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhao et al., 2015] Fang Zhao, Yongzhen Huang, Liang Wang, and Tieniu Tan. Deep semantic ranking based hash- ing for multi-label image retrieval. In CVPR, pages 1556- 1564, 2015.","title":"Deep semantic ranking based hashing for multi-label image retrieval","authors":"Fang Zhao, Yongzhen Huang, Liang Wang, Tieniu Tan","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zheng et al., 2015] Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. Scalable person re-identification: A benchmark. In ICCV, pages 1116-1124, 2015.","title":"Scalable person re-identification: A benchmark","authors":"Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, Qi Tian","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhou et al., 2016] Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. Dorefa-net: Train- ing low bitwidth convolutional neural networks with low bitwidth gradients. In arXiv:1606.06160, 2016.","title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","authors":"Zhou","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhu et al., 2016] Han Zhu, Mingsheng Long, Jianmin- Wang, and Yue Cao. Deep hashing network for efficient similarity retrieval. In AAAI, pages 2415-2421, 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},{"position":38,"raw":"[Zhu et al., 2017] Chenzhuo Zhu, Song Han, Huizi Mao, and William J. Dally. Trained ternary quantization. In LCLR, 2017.","title":"Trained ternary quantization","authors":"Zhu","year":"2017","venue":"LCLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}