{"type":"ScholarlyArticle","title":"Channel-Level Variable Quantization Network for Deep Image Compression","authors":[{"name":"Zhisheng Zhong","slug":"zhisheng-zhong","given":"Zhisheng","family":"Zhong","affiliation":"The University of Tokyo , Japan"},{"name":"Hiroaki Akutsu","slug":"hiroaki-akutsu","given":"Hiroaki","family":"Akutsu","affiliation":"Hitachi Ltd , Japan"},{"name":"Kiyoharu Aizawa","slug":"kiyoharu-aizawa","given":"Kiyoharu","family":"Aizawa","affiliation":"The University of Tokyo , Japan"}],"abstract":"Deep image compression systems mainly contain four components: encoder, quantizer, entropy model, and decoder. To optimize these four components, a joint rate-distortion framework was proposed, and many deep neural network-based methods achieved great success in image compression. However, almost all convolutional neural network-based methods treat channel-wise feature maps equally, reducing the flexibility in handling different types of information. In this paper, we propose a channel-level variable quantization network to dynamically allocate more bitrates for significant channels and withdraw bitrates for negligible channels. Specifically, we propose a variable quantization controller. It consists of two key components: the channel importance module, which can dynamically learn the importance of channels during training, and the splitting-merging module, which can allocate different bitrates for different channels. We also formulate the quantizer into a Gaussian mixture model manner. Quantitative and qualitative experiments verify the effectiveness of the proposed model and demonstrate that our method achieves superior performance and can produce much better visual reconstructions.","doi":"10.24963/ijcai.2020/65","url":"https://ijcai.org/proceedings/2020/65","pdf":"https://ijcai.org/proceedings/2020/0065.pdf","markdown":"https://ijcai.org/proceedings/2020/65.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/65","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Computer Vision","track":"Main track","number":65,"pages":{"first":467,"last":473},"keywords":["Machine Learning: Deep Learning: Convolutional networks","Computer Vision: Other","Machine Learning: Deep Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24362/file_24362.m3u8","length_sec":311,"provider":"hls"}],"references":[{"position":1,"raw":"[Agustsson et al., 2017] Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli, et al. Soft-to-hard vector quantization for end-to-end learning compressible representa- tions. In NeurIPS, pages 1141-1151, 2017.","title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","authors":"Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Agustsson et al., 2019] Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, and Luc Van Gool. Generative adversarial networks for extreme learned image compression. In ICCV, pages 221-231, 2019.","title":"Generative adversarial networks for extreme learned image compression","authors":"Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, Luc Van Gool","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ballé et al., 2017] Johannes Ballé, Valero Laparra, and Eero P Si- moncelli. End-to-end optimized image compression. In ICLR, 2017.","title":"End-to-end optimized image compression","authors":"Johannes Ballé, Valero Laparra, Eero P Simoncelli","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ballé et al., 2018] Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. Variational image compres- sion with a scale hyperprior. In ICLR, 2018.","title":"Variational image compression with a scale hyperprior","authors":"Johannes Ballé, David Minnen, Saurabh Singh, Sung, Jin Hwang, Nick Johnston","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cover and Thomas, 2012] Thomas M Cover and Joy A Thomas. Elements of information theory. John Wiley & Sons, 2012.","title":"Elements of information theory","authors":"M Thomas, Joy A Cover, Thomas","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong et al., 2014] Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Learning a deep convolutional network for image super-resolution. In ECCV, pages 184-199, 2014.","title":"Learning a deep convolutional network for image super-resolution","authors":"Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2017] Yihui He, Xiangyu Zhang, and Jian Sun. Channel pruning for accelerating very deep neural networks. In ICCV, pages 1389-1397, 2017.","title":"Channel pruning for accelerating very deep neural networks","authors":"Yihui He, Xiangyu Zhang, Jian Sun","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2018] Jie Hu, Li Shen, and Gang Sun. Squeeze-and- excitation networks. In CVPR, pages 7132-7141, 2018.","title":"Squeeze-andexcitation networks","authors":"Jie Hu, Li Shen, Gang Sun","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Johnston et al., 2018] Nick Johnston, Damien Vincent, David Minnen, Michele Covell, Saurabh Singh, et al. Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks. In CVPR, pages 4385-4393, 2018.","title":"Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks","authors":"Nick Johnston, Damien Vincent, David Minnen, Michele Covell, Saurabh Singh","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2015] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Ge- offrey E Hinton. Imagenet classification with deep convolutional neural networks. In NeurIPS, pages 1097-1105, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lee et al., 2019] Jooyoung Lee, Seunghyun Cho, and Seung- Kwon Beack. Context-adaptive entropy model for end-to-end optimized image compression. In ICLR, 2019.","title":"Context-adaptive entropy model for end-to-end optimized image compression","authors":"Lee","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2018] Mu Li, Wangmeng Zuo, Shuhang Gu, Debin Zhao, and David Zhang. Learning convolutional networks for content- weighted image compression. In CVPR, pages 3214-3223, 2018.","title":"Learning convolutional networks for contentweighted image compression","authors":"Mu Li, Wangmeng Zuo, Shuhang Gu, Debin Zhao, David Zhang","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lim et al., 2017] Bee Lim, Sanghyun Son, Heewon Kim, Se- ungjun Nah, and Kyoung Mu Lee. Enhanced deep residual net- works for single image super-resolution. In CVPR Workshops, pages 136-144, 2017.","title":"Enhanced deep residual networks for single image super-resolution","authors":"Lim","year":"2017","venue":"CVPR Workshops","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2017] Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, and Changshui Zhang. Learning efficient convolutional networks through network slimming. In ICCV, pages 2736-2744, 2017.","title":"Learning efficient convolutional networks through network slimming","authors":"Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2019] Zhuang Liu, Mingjie Sun, Tinghui Zhou, Gao Huang, and Trevor Darrell. Rethinking the value of network pruning. ICLR, 2019.","title":"Rethinking the value of network pruning","authors":"Zhuang Liu, Mingjie Sun, Tinghui Zhou, Gao Huang, Trevor Darrell","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Luo et al., 2017] Jian-Hao Luo, Jianxin Wu, and Weiyao Lin. ThiNet: A filter level pruning method for deep neural network compression. In ICCV, pages 5058-5066, 2017.","title":"ThiNet: A filter level pruning method for deep neural network compression","authors":"Jian-Hao Luo, Jianxin Wu, Weiyao Lin","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mentzer et al., 2018] Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, and Luc Van Gool. Conditional prob- ability models for deep image compression. In CVPR, pages 4394-4402, 2018.","title":"Conditional probability models for deep image compression","authors":"Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc Van Gool","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Minnen et al., 2018] David Minnen, Johannes Ballé, and George D Toderici. Joint autoregressive and hierarchical priors for learned image compression. In NeurIPS, pages 10771-10780, 2018.","title":"Joint autoregressive and hierarchical priors for learned image compression","authors":"David Minnen, Johannes Ballé, George D Toderici","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rippel and Bourdev, 2017] Oren Rippel and Lubomir Bourdev. Real-time adaptive image compression. In ICML, pages 2922- 2930, 2017.","title":"Real-time adaptive image compression","authors":"Oren Rippel, Lubomir Bourdev","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Russakovsky et al., 2015] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, 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","year":"2015","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shi et al., 2016] Wenzhe Shi, Jose Caballero, Ferenc Huszár, Jo- hannes Totz, et al. Real-time single image and video super- resolution using an efficient sub-pixel convolutional neural net- work. In CVPR, pages 1874-1883, 2016.","title":"Real-time single image and video superresolution using an efficient sub-pixel convolutional neural network","authors":"Shi","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Skodras et al., 2001] Athanassios Skodras, Charilaos Christopou- los, and Touradj Ebrahimi. The JPEG 2000 still image compres- sion standard. IEEE Signal Processing Magazine, 18(5):36-58, 2001.","title":"The JPEG 2000 still image compression standard","authors":"Athanassios Skodras, Charilaos Christopoulos, Touradj Ebrahimi","year":"2001","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Thomee et al., 2016] Bart Thomee, David A Shamma, Gerald Friedland, Benjamin Elizalde, Karl Ni, Douglas Poland, Damian Borth, and Li-Jia Li. YFCC100M: The new data in multimedia research. Communications of the ACM, 59(2):64-73, 2016.","title":"YFCC100M: The new data in multimedia research","authors":"Bart Thomee, David A Shamma, Gerald Friedland, Benjamin Elizalde, Karl Ni, Douglas Poland, Damian Borth, Li-Jia Li","year":"2016","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Timofte et al., 2017] Radu Timofte, Eirikur Agustsson, Luc Van Gool, Ming-Hsuan Yang, and Lei Zhang. NTIRE 2017 chal- lenge on single image super-resolution: Methods and results. In CVPR Workshops, pages 114-125, 2017.","title":"NTIRE 2017 challenge on single image super-resolution: Methods and results","authors":"Radu Timofte, Eirikur Agustsson, Luc Van Gool, Ming-Hsuan Yang, Lei Zhang","year":"2017","venue":"CVPR Workshops","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Toderici et al., 2016] George Toderici, Sean M O'Malley, Sung Jin Hwang, Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, and Rahul Sukthankar. Variable rate image com- pression with recurrent neural networks. In ICLR, 2016.","title":"Variable rate image compression with recurrent neural networks","authors":"George Toderici, M O' Sean, Sung Malley, Jin Hwang, Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, Rahul Sukthankar","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Toderici et al., 2017] George Toderici, Damien Vincent, Nick Johnston, Sung Jin Hwang, David Minnen, Joel Shor, and Michele Covell. Full resolution image compression with recur- rent neural networks. In CVPR, pages 5306-5314, 2017.","title":"Full resolution image compression with recurrent neural networks","authors":"George Toderici, Damien Vincent, Nick Johnston, Sung, Jin Hwang, David Minnen, Joel Shor, Michele Covell","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Van Oord et al., 2016] Aaron Van Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. Pixel recurrent neural networks. In ICML, pages 1747-1756, 2016.","title":"Pixel recurrent neural networks","authors":"Van Oord","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wallace, 1992] Gregory K Wallace. The JPEG still picture com- pression standard. IEEE Transactions on Consumer Electronics, 38(1), 1992.","title":"The JPEG still picture compression standard","authors":"Wallace Gregory","year":"1992","venue":"IEEE Transactions on Consumer Electronics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wang et al., 2003] Zhou Wang, Eero P Simoncelli, and Alan C Bovik. Multiscale structural similarity for image quality assess- ment. In Asilomar Conference on Signals, Systems & Computers, volume 2, pages 1398-1402, 2003.","title":"Multiscale structural similarity for image quality assessment","authors":"Zhou Wang, Eero P Simoncelli, Alan C Bovik","year":"2003","venue":"Asilomar Conference on Signals, Systems & Computers","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang et al., 2018] Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image super-resolution using very deep residual channel attention networks. In ECCV, pages 286-301, 2018.","title":"Image super-resolution using very deep residual channel attention networks","authors":"Zhang","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhong et al., 2018] Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, and Chao Zhang. Joint sub-bands learning with clique structures for wavelet domain super-resolution. In NeurIPS, pages 165-175, 2018.","title":"Joint sub-bands learning with clique structures for wavelet domain super-resolution","authors":"Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhu et al., 2017] Chenzhuo Zhu, Song Han, Huizi Mao, and William J Dally. Trained ternary quantization. In ICLR, 2017.","title":"Trained ternary quantization","authors":"Zhu","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}