{"type":"ScholarlyArticle","title":"Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs","authors":[{"name":"Chunlei Liu","slug":"chunlei-liu","given":"Chunlei","family":"Liu","affiliation":"School of Electronic and Information Engineering , Beihang University"},{"name":"Wenrui Ding","slug":"wenrui-ding","given":"Wenrui","family":"Ding","affiliation":"Unmanned System Research Institute , Beihang University"},{"name":"Xin Xia","slug":"xin-xia","given":"Xin","family":"Xia","affiliation":"School of Electronic and Information Engineering , Beihang University"},{"name":"Yuan Hu","slug":"yuan-hu","given":"Yuan","family":"Hu","affiliation":"School of Electronic and Information Engineering , Beihang University"},{"name":"Baochang Zhang","slug":"baochang-zhang","given":"Baochang","family":"Zhang","affiliation":"School of Automation Science and Electrical Engineering , Beihang University"},{"name":"Jianzhuang Liu","slug":"jianzhuang-liu","given":"Jianzhuang","family":"Liu","affiliation":"Huawei Noah's Ark Lab"},{"name":"Bohan Zhuang","slug":"bohan-zhuang","given":"Bohan","family":"Zhuang","affiliation":"The University of Adelaide , Australia"},{"name":"Guodong Guo","slug":"guodong-guo","given":"Guodong","family":"Guo","affiliation":"Institute of Deep Learning , Baidu Research; National Engineering Laboratory for Deep Learning Technology and Application"}],"abstract":"Binarized  convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the 1-bit binary network with the guidance of its corresponding full-precision model, which significantly improves the performance of BCNNs. The rectified convolutional layers are generic and flexible, and can be easily incorporated into existing DCNNs such as WideResNets and ResNets. Extensive experiments demonstrate the superior performance of the proposed RBCNs over state-of-the-art BCNNs. In particular, our method shows strong generalization on the object tracking task.","doi":"10.24963/ijcai.2019/120","url":"https://ijcai.org/proceedings/2019/120","pdf":"https://ijcai.org/proceedings/2019/0120.pdf","markdown":"https://ijcai.org/proceedings/2019/120.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/120","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":120,"pages":{"first":854,"last":860},"keywords":["Computer Vision: Motion and Tracking","Computer Vision: Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Courbariaux et al., 2016] Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv preprint arXiv:1602.02830, 2016.","title":"Binarized neural networks: Training deep 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":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Gu et al., 2019] Jiaxin Gu, Baochang Zhang, and Jianzhuang Liu. Projection convolutional neural networks. In AAAI, 2019.","title":"Projection convolutional neural networks","authors":"Jiaxin Gu, Baochang Zhang, Jianzhuang Liu","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Hou et al., 2016] Lu Hou, Quanming Yao, and James T Kwok. Loss-aware binarization of deep networks. arXiv preprint arXiv:1611.01600, 2016.","title":"Loss-aware binarization of deep networks","authors":"Lu Hou, Quanming Yao, James T Kwok","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Huang et al., 2018] Lianghua Huang, Xin Zhao, and Kaiqi Huang. Got-10k: A large high-diversity benchmark for generic object tracking in the wild. arXiv preprint arXiv:1810.11981, 2018.","title":"Got-10k: A large high-diversity benchmark for generic object tracking in the wild","authors":"Huang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Krizhevsky and Hinton, 2009] Nair Krizhevsky and Hinton. The cifar-10 dataset. online: http://www. cs. toronto. edu/kriz/cifar. html, 2009.","title":"Nair Krizhevsky and Hinton. The cifar-10 dataset","authors":"Hinton Krizhevsky","year":"2009","venue":null,"doi":null,"url":"http://www.cs.toronto.edu/kriz/cifar.html","internal_url":null},{"position":7,"raw":"[Lecun et al., 1998] Yann Lecun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Leon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lin et al., 2017] Xiaofan Lin, Cong Zhao, and Wei Pan. Towards accurate binary convolutional neural network. In Advances in Neural Information Processing Systems, pages 345-353, 2017.","title":"Towards accurate binary convolutional neural network","authors":"Xiaofan Lin, Cong Zhao, Wei Pan","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2018] Zechun Liu, Baoyuan Wu, Wenhan Luo, Xin Yang, Wei Liu, and Kwang-Ting Cheng. Bi- real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm. In Proceedings of the European Conference on Computer Vision, pages 722-737, 2018.","title":"Bireal net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm","authors":"Liu","year":"2018","venue":"Proceedings of the European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mishra and Marr, 2017] Asit Mishra and Debbie Marr. Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy. arX- iv:1711.05852v1, 2017.","title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","authors":"Marr Mishra, Asit Mishra, Debbie Marr","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mueller et al., 2016] Matthias Mueller, Neil Smith, and Bernard Ghanem. A benchmark and simulator for uav tracking. In European conference on computer vision, pages 445-461. Springer, 2016.","title":"A benchmark and simulator for uav tracking","authors":"Matthias Mueller, Neil Smith, Bernard Ghanem","year":"2016","venue":"European conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Polino et al., 2018] Antonio Polino, Razvan Pascanu, and Alistarh Dan. Model compression via distillation and quantization. arXiv:1802.05668v1, 2018.","title":"Model compression via distillation and quantization","authors":"Polino","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Rastegari et al., 2016] Mohammad Rastegari, Vicente Or- donez, Joseph Redmon, and Ali Farhadi. Xnor-net: Imagenet classification using binary convolutional neural networks. In European Conference on Computer Vision, pages 525-542, 2016.","title":"Xnor-net: Imagenet classification using binary convolutional neural networks","authors":"Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi","year":"2016","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Russakovsky et al., 2015] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, and Michael Bernstein. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 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":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wang et al., 2018] Xiaodi Wang, Baochang Zhang, Ce Li, Rongrong Ji, Jungong Han, Xianbin Cao, and Jianzhuang Liu. Modulated convolutional networks. In The IEEE Conference on Computer Vision and Pattern Recognition, June 2018.","title":"Modulated convolutional networks","authors":"Xiaodi Wang, Baochang Zhang, Ce Li, Rongrong Ji, Jungong Han, Xianbin Cao, Jianzhuang Liu","year":"2018","venue":"The IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wu et al., 2013] Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. Online object tracking: A benchmark. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2411-2418, 2013.","title":"Online object tracking: A benchmark","authors":"Yi Wu, Jongwoo Lim, Ming-Hsuan Yang","year":"2013","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wu et al., 2015] Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9):1834- 1848, 2015.","title":"Object tracking benchmark","authors":"Yi Wu, Jongwoo Lim, Ming-Hsuan Yang","year":"2015","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Zagoruyko and Komodakis, 2016] Sergey Zagoruyko and Nikos Komodakis. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.","title":"Wide residual networks","authors":"Sergey Zagoruyko, Nikos Komodakis","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhou et al., 2017] Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, and Yurong Chen. Incremental network quantization: Towards lossless cnns with low-precision weights. arXiv preprint arXiv:1702.03044, 2017.","title":"Incremental network quantization: Towards lossless cnns with low-precision weights","authors":"Zhou","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhu et al., 2016] Chenzhuo Zhu, Song Han, Huizi Mao, and William J Dally. Trained ternary quantization. arXiv preprint arXiv:1612.01064, 2016.","title":"Trained ternary quantization","authors":"Zhu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhuang et al., 2018] Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, and Ian Reid. Towards effective low-bitwidth convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7920-7928, 2018.","title":"Towards effective low-bitwidth convolutional neural networks","authors":"Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid","year":"2018","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."}