{"type":"ScholarlyArticle","title":"Hypergraph Induced Convolutional Manifold Networks","authors":[{"name":"Taisong Jin","slug":"taisong-jin","given":"Taisong","family":"Jin","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart City , School of Information Science and Engineering , Xiamen University , 361005 , China; Science and Technology on Electro-Optical Control Laboratory , Luoyang , 471023 , China"},{"name":"Liujuan Cao","slug":"liujuan-cao","given":"Liujuan","family":"Cao","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart City , School of Information Science and Engineering , Xiamen University , 361005 , China"},{"name":"Baochang Zhang","slug":"baochang-zhang","given":"Baochang","family":"Zhang","affiliation":"School of Automation Science and Electrical Engineering , Beihang University , 100083 , China"},{"name":"Xiaoshuai Sun","slug":"xiaoshuai-sun","given":"Xiaoshuai","family":"Sun","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart City , School of Information Science and Engineering , Xiamen University , 361005 , China"},{"name":"Cheng Deng","slug":"cheng-deng","given":"Cheng","family":"Deng","affiliation":"School of Electronic Engineering , Xidian University , 710071 , China"},{"name":"Rongrong Ji","slug":"rongrong-ji","given":"Rongrong","family":"Ji","affiliation":"Fujian Key Laboratory of Sensing and Computing for Smart City , School of Information Science and Engineering , Xiamen University , 361005 , China"}],"abstract":"Deep convolutional neural networks (DCNN) with manifold embedding have achieved considerable attention in computer vision. However, prior arts are usually based on the neighborhood-based graph modeling only the pairwise relationship between two samples, which fail to fully capture intra-class variations and thus suffer from severe performance loss for noisy data. While such intra-class variations can be well captured via sophisticated hypergraph structure, we are motivated and lead a hypergraph induced Convolutional Manifold Network (H-CMN) to significantly improve the representation capacity of DCNN for the complex data. Specifically, two innovative designs are provides: 1) our manifold preserving method is implemented based on a mini-batch, which can be efficiently plugged into the existing DCNN training pipelines and be scalable for large datasets; 2) a robust hypergraph is built for each mini-batch, which not only offers a strong robustness against typical noise, but also captures the variances from multiple features. Extensive experiments on the image classification task on large benchmarking datasets demonstrate that our model achieves much better performance than the state-of-the-art","doi":"10.24963/ijcai.2019/371","url":"https://ijcai.org/proceedings/2019/371","pdf":"https://ijcai.org/proceedings/2019/0371.pdf","markdown":"https://ijcai.org/proceedings/2019/371.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/371","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":"Machine Learning A-L","track":"Main track","number":371,"pages":{"first":2670,"last":2676},"keywords":["Computer Vision: Computer Vision","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Agarwal et al., 2005] Sameer Agarwal, Jongwoo Lim, Lihi Zelnik-Manor, Pietro Perona, David Kriegman, and Serge Belongie. Beyond pairwise clustering. In CVPR, vol- ume 2, pages 838-845, 2005.","title":"Beyond pairwise clustering","authors":"Sameer Agarwal, Jongwoo Lim, Lihi Zelnik-Manor, Pietro Perona, David Kriegman, Serge Belongie","year":"2005","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Belkin et al., 2006] Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. Manifold regularization: A geometric framework for learning from labeled and unlabeled exam- ples. J. Mach. Learn. Res., 7:2399-2434, 2006.","title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","authors":"Mikhail Belkin, Partha Niyogi, Vikas Sindhwani","year":"2006","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Elhamifar and Vidal, 2013] Ehsan Elhamifar and Rene Vi- dal. Sparse subspace clustering: Algorithm, theory, and applications. IEEE Trans. Pattern Anal. Mach. Intell., 35(11):2765-2781, 2013.","title":"Sparse subspace clustering: Algorithm, theory, and applications","authors":"Ehsan Elhamifar, Rene Vidal","year":"2013","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gao et al., 2013] Shenghua Gao, Ivor Wai-Hung Tsang, and Liang-Tien Chia. Laplacian sparse coding, hypergraph laplacian sparse coding, and applications. IEEE Trans. Pattern Anal. Mach. Intell., 35(1):92-104, 2013.","title":"Laplacian sparse coding, hypergraph laplacian sparse coding, and applications","authors":"Shenghua Gao, Ivor Wai-Hung, Liang-Tien Tsang, Chia","year":"2013","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2014] Yue Gao, Rongrong Ji, Peng Cui, Qiong- hai Dai, and Gang Hua. Hyperspectral image classification through bilayer graph-based learning. IEEE Trans. Image Process., 23(7):2769-2778, 2014.","title":"Hyperspectral image classification through bilayer graph-based learning","authors":"Yue Gao, Rongrong Ji, Peng Cui, Qionghai Dai, Gang Hua","year":"2014","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Han et al., 2017] Bohyung Han, Jack Sim, and Hartwig Adam. Branchout: Regularization for online ensemble tracking with convolutional neural networks. In CVPR, pages 521-530, 2017.","title":"Branchout: Regularization for online ensemble tracking with convolutional neural networks","authors":"Han","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He and Niyogi, 2003] Xiaofei He and Partha Niyogi. Local- ity preserving projections. In NIPS, pages 153-160, 2003.","title":"Locality preserving projections","authors":"Xiaofei He, Partha Niyogi","year":"2003","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. 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":9,"raw":"[Howard et al., 2017] Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mo- bilenets: efficient convolutional neural networks for mo- bile vision applications. CoRR, abs/1704.04861, 2017.","title":"Mobilenets: efficient convolutional neural networks for mobile vision applications","authors":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2010] Yuchi Huang, Qingshan Liu, Shaoting Zhang, and Dimitris N Metaxas. Image retrieval via prob- abilistic hypergraph ranking. In CVPR, pages 3376-3383, 2010.","title":"Image retrieval via probabilistic hypergraph ranking","authors":"Yuchi Huang, Qingshan Liu, Shaoting Zhang, Dimitris N Metaxas","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Huang et al., 2015] Sheng Huang, Mohamed Elhoseiny, Ahmed Elgammal, and Dan Yang. Learning hypergraph- regularized attribute predictors. In CVPR, pages 409-417, 2015.","title":"Learning hypergraphregularized attribute predictors","authors":"Sheng Huang, Mohamed Elhoseiny, Ahmed Elgammal, Dan Yang","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krizhevsky, 2009] Alex Krizhevsky. Learning multiple lay- ers of features from tiny images. 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":13,"raw":"[Liu et al., 2013] Guangcan Liu, Zhouchen Lin, Shuicheng Yan, Ju Sun, Yong Yu, and Yi Ma. Robust recovery of sub- space structures by low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell., 35(1):171-184, 2013.","title":"Robust recovery of subspace structures by low-rank representation","authors":"Liu","year":"2013","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2017] Qingshan Liu, Yubao Sun, Cantian Wang, Tongliang Liu, and Dacheng Tao. Elastic net hypergraph learning for image clustering and semi-supervised classifi- cation. IEEE Trans. Image Process., 26(1):452-463, 2017.","title":"Elastic net hypergraph learning for image clustering and semi-supervised classification","authors":"Qingshan Liu, Yubao Sun, Cantian Wang, Tongliang Liu, Dacheng Tao","year":"2017","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lu et al., 2015] Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, and Jie Zhou. Multi-manifold deep met- ric learning for image set classification. In CVPR, pages 1137-1145, 2015.","title":"Multi-manifold deep metric learning for image set classification","authors":"Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, Jie Zhou","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Netzer et al., 2012] Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y Ng. Reading digits in natural images with unsupervised feature learn- ing. 2012.","title":"Reading digits in natural images with unsupervised feature learning","authors":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y Ng","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rifai et al., 2011] Salah Rifai, Yann N Dauphin, Pascal Vin- cent, Yoshua Bengio, and Xavier Muller. The manifold tangent classifier. In NIPS, pages 2294-2302, 2011.","title":"The manifold tangent classifier","authors":"Salah Rifai, Pascal Yann N Dauphin, Yoshua Vincent, Xavier Bengio, Muller","year":"2011","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Two-stream convolutional networks for action recognition in videos. NIPS, 1(4):568-576, 2014.","title":"Two-stream convolutional networks for action recognition in videos","authors":"Zisserman Simonyan","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":19,"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":20,"raw":"[Szegedy et al., 2016] Christian Szegedy, Sergey Ioffe, Vin- cent Vanhoucke, and Alexander A Alemi. Inception-v4, inception-resnet and the impact of residual connections on learning. pages 4278-4284, 2016.","title":"Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, and Alexander A Alemi. Inception-v4, inception-resnet and the impact of residual connections on learning","authors":"Szegedy","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tomar and Rose, 2014] Vikrant Singh Tomar and Richard C Rose. Manifold regularized deep neural networks. In In- terspeech, 2014.","title":"Manifold regularized deep neural networks","authors":"Singh Vikrant, Richard C Tomar, Rose","year":"2014","venue":"Interspeech","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2015a] Limin Wang, Yu Qiao, and Xiaoou Tang. Action recognition with trajectory-pooled deep- convolutional descriptors. In CVPR, pages 4305-4314, 2015.","title":"Action recognition with trajectory-pooled deepconvolutional descriptors","authors":"Wang","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2015b] Meng Wang, Xueliang Liu, and Xin- dong Wu. Visual classification by ℓ 1 -hypergraph model- ing. IEEE Trans. Knowl. Data Eng., 27(9):2564-2574, 2015.","title":"Visual classification by ℓ 1 -hypergraph modeling","authors":"Wang","year":"2015","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wen et al., 2016a] Yandong Wen, Zhifeng Li, and Yu Qiao. Latent factor guided convolutional neural networks for age-invariant face recognition. In CVPR, pages 4893- 4901, 2016.","title":"Latent factor guided convolutional neural networks for age-invariant face recognition","authors":"Wen","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wen et al., 2016b] Yandong Wen, Kaipeng Zhang, Zhifeng Li, and Yu Qiao. A discriminative feature learning ap- proach for deep face recognition. In ECCV, pages 499- 515, 2016.","title":"A discriminative feature learning approach for deep face recognition","authors":"Wen","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yang et al., 2017] Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang, and Qingming Huang. A graph regular- ized deep neural network for unsupervised image repre- sentation learning. In CVPR, pages 7053-7061, 2017.","title":"A graph regularized deep neural network for unsupervised image representation learning","authors":"Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang, Qingming Huang","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yuan et al., 2015] Yuan Yuan, Lichao Mou, and Xiaoqiang Lu. Scene recognition by manifold regularized deep learn- ing architecture. IEEE Trans. Neural Netw., 26(10):2222- 2233, 2015.","title":"Scene recognition by manifold regularized deep learning architecture","authors":"Yuan Yuan, Lichao Mou, Xiaoqiang Lu","year":"2015","venue":"IEEE Trans. Neural Netw","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zagoruyko and Komodakis, 2016] Sergey Zagoruyko and Nikos Komodakis. Wide residual networks. In BMVC, 2016.","title":"Wide residual networks","authors":"Sergey Zagoruyko, Nikos Komodakis","year":"2016","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2017] Zhihong Zhang, Lu Bai, Yuanheng Liang, and Edwin Hancock. Joint hypergraph learning and sparse regression for feature selection. Pattern Recognit., 63:291-309, 2017.","title":"Joint hypergraph learning and sparse regression for feature selection","authors":"Zhihong Zhang, Lu Bai, Yuanheng Liang, Edwin Hancock","year":"2017","venue":"Pattern Recognit","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}