{"type":"ScholarlyArticle","title":"Coarse-to-fine Image Co-segmentation with Intra and Inter Rank Constraints","authors":[{"name":"Lianli Gao","slug":"lianli-gao","given":"Lianli","family":"Gao","affiliation":"Center for Future Media and School of Computer Science and Engineering , University of Electronic Science and Technology of China , Chengdu 611731 , China"},{"name":"Jingkuan Song","slug":"jingkuan-song","given":"Jingkuan","family":"Song","affiliation":"Center for Future Media and School of Computer Science and Engineering , University of Electronic Science and Technology of China , Chengdu 611731 , China"},{"name":"Dongxiang Zhang","slug":"dongxiang-zhang","given":"Dongxiang","family":"Zhang","affiliation":"Center for Future Media and School of Computer Science and Engineering , University of Electronic Science and Technology of China , Chengdu 611731 , China"},{"name":"Heng Tao Shen","slug":"heng-tao-shen","given":"Heng Tao","family":"Shen","affiliation":"Center for Future Media and School of Computer Science and Engineering , University of Electronic Science and Technology of China , Chengdu 611731 , China"}],"abstract":"Image co-segmentation is the problem of automatically discovering the common objects co-occurring in a set of relevant images and segmenting them as foreground simultaneously. Although a bunch of approaches have been proposed to address this problem, many of them still suffer from certain limitations, e.g., supervised feature learning and complex models, which hinder their capability in the real-world scenarios. \r\nTo alleviate these limitations, we propose a novel coarse-to-fine co-segmentation (CFC) framework, which utilizes the coarse foreground and background proposals to learn a robust similarity measure of the features in an unsupervised way, and then devises a simple objective function based on the definition of image co-segmentation. \r\nSpecifically, we first generate superpixels for all the images and extract their features. Instead of using existing distance metrics, we utilize object proposal methods to generate coarse foreground and background to learn a similarity measure of superpixels to construct a robust feature similarity graph. Then we design an intuitive objective function to learn a segmentation similarity graph which should be consistent with feature similarity graph and also be able to co-segment the superpixels in the images into either foreground and background. This objective function can be further reformulated as a graph learning problem with intra and inter rank constraints. Experiments on two commonly used image datasets (iCoseg and MSRC) demonstrate that CFC outperforms other state-of-the-art methods. Notably, this performance is achieved by using only HSV feature.","doi":"10.24963/ijcai.2018/100","url":"https://ijcai.org/proceedings/2018/100","pdf":"https://ijcai.org/proceedings/2018/0100.pdf","markdown":"https://ijcai.org/proceedings/2018/100.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/100","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":"Computer Vision","track":"Main track","number":100,"pages":{"first":719,"last":725},"keywords":["Machine Learning: Machine Learning","Computer Vision: Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Arbeláez et al., 2014] Pablo Andrés Arbeláez, Jordi Pont- Tuset, Jonathan T. Barron, Ferran Marqués, and Jitendra Malik. Multiscale combinatorial grouping. In CVPR, pages 328-335, 2014.","title":"Multiscale combinatorial grouping","authors":"Arbeláez","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Batra et al., 2010] Dhruv Batra, Adarsh Kowdle, Devi Parikh, Jiebo Luo, and Tsuhan Chen. icoseg: Interac- tive co-segmentation with intelligent scribble guidance. In CVPR, pages 3169-3176, 2010.","title":"icoseg: Interactive co-segmentation with intelligent scribble guidance","authors":"Dhruv Batra, Adarsh Kowdle, Devi Parikh, Jiebo Luo, Tsuhan Chen","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chatfield et al., 2014] Ken Chatfield, Karen Simonyan, An- drea Vedaldi, and Andrew Zisserman. Return of the devil in the details: Delving deep into convolutional nets. In BMVC, 2014.","title":"Return of the devil in the details: Delving deep into convolutional nets","authors":"Ken Chatfield, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman","year":"2014","venue":"BMVC","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fan, 1949] Ky Fan. On a theorem of weyl concerning eigen- values of linear transformations i. Proceedings of the Na- tional Academy of Sciences of the United States of Amer- ica, 35(11):652, 1949.","title":"On a theorem of weyl concerning eigenvalues of linear transformations i","authors":"Fan Ky","year":"1949","venue":"Proceedings of the National Academy of Sciences of the United States of America","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2016] Lianli Gao, Jingkuan Song, Feiping Nie, Fuhao Zou, Nicu Sebe, and Heng Tao Shen. Graph- without-cut: An ideal graph learning for image segmen- tation. In AAAI, pages 1188-1194, 2016.","title":"Graphwithout-cut: An ideal graph learning for image segmentation","authors":"Gao","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Joulin et al., 2010] Armand Joulin, Francis R. Bach, and Jean Ponce. Discriminative clustering for image co- segmentation. In CVPR, pages 1943-1950, 2010.","title":"Discriminative clustering for image cosegmentation","authors":"Armand Joulin, Francis R Bach, Jean Ponce","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lee et al., 2015] Chulwoo Lee, Won-Dong Jang, Jae-Young Sim, and Chang-Su Kim. Multiple random walkers and their application to image cosegmentation. In CVPR, pages 3837-3845, 2015.","title":"Multiple random walkers and their application to image cosegmentation","authors":"Lee","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2016] Kunqian Li, Jiaojiao Zhang, and Wenbing Tao. Unsupervised co-segmentation for indefinite number of common foreground objects. IEEE Trans. Image Pro- cessing, 25(4):1898-1909, 2016.","title":"Unsupervised co-segmentation for indefinite number of common foreground objects","authors":"Li","year":"2016","venue":"IEEE Trans. Image Processing","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Maninis et al., 2017] Kevis-Kokitsi Maninis, Sergi Caelles, Jordi Pont-Tuset, and Luc Van Gool. Deep extreme cut: From extreme points to object segmentation. CoRR, abs/1711.09081, 2017.","title":"Deep extreme cut: From extreme points to object segmentation","authors":"Maninis","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Margolin et al., 2013] Ran Margolin, Ayellet Tal, and Lihi Zelnik-Manor. What makes a patch distinct? In Proceed- ings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR '13, pages 1139-1146, Wash- ington, DC, USA, 2013. IEEE Computer Society.","title":"What makes a patch distinct?","authors":"Ran Margolin, Ayellet Tal, Lihi Zelnik-Manor","year":"2013","venue":"Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Meng et al., 2012] Fanman Meng, Hongliang Li, Guanghui Liu, and King Ngi Ngan. Object co-segmentation based on shortest path algorithm and saliency model. IEEE Trans. Multimedia, 14(5):1429-1441, 2012.","title":"Object co-segmentation based on shortest path algorithm and saliency model","authors":"Fanman Meng, Hongliang Li, Guanghui Liu, King Ngi, Ngan","year":"2012","venue":"IEEE Trans. Multimedia","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Meng et al., 2013] Fanman Meng, Hongliang Li, King Ngi Ngan, Liaoyuan Zeng, and Qingbo Wu. Feature adaptive co-segmentation by complexity awareness. IEEE Trans. Image Processing, 22(12):4809-4824, 2013.","title":"Feature adaptive co-segmentation by complexity awareness","authors":"Fanman Meng, Hongliang Li, King Ngi Ngan, Liaoyuan Zeng, Qingbo Wu","year":"2013","venue":"IEEE Trans. Image Processing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mukherjee et al., 2018] Prerana Mukherjee, Brejesh Lall, and Snehith Lattupally. Object cosegmentation using deep siamese network. CoRR, abs/1803.02555, 2018.","title":"Object cosegmentation using deep siamese network","authors":"Prerana Mukherjee, Brejesh Lall, Snehith Lattupally","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nie et al., 2016] Feiping Nie, Xiaoqian Wang, Michael I. Jordan, and Heng Huang. The constrained laplacian rank algorithm for graph-based clustering. In AAAI, pages 1969-1976, 2016.","title":"The constrained laplacian rank algorithm for graph-based clustering","authors":"Nie","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Rubio, 2012] José C. Rubio. Unsupervised co-segmentation through region matching. In CVPR, pages 749-756, 2012.","title":"Unsupervised co-segmentation through region matching","authors":"C José, Rubio","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Shi and Malik, 2000] Jianbo Shi and Jitendra Malik. Nor- malized cuts and image segmentation. IEEE Trans. Pat- tern Anal. Mach. Intell., 22(8):888-905, 2000.","title":"Normalized cuts and image segmentation","authors":"Jianbo Shi, Jitendra Malik","year":"2000","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Song et al., 2016] Jingkuan Song, Lianli Gao, Mihai Mar- ian Puscas, Feiping Nie, Fumin Shen, and Nicu Sebe. Joint graph learning and video segmentation via multiple cues and topology calibration. In ACM Multimedia, pages 831- 840, 2016.","title":"Joint graph learning and video segmentation via multiple cues and topology calibration","authors":"Song","year":"2016","venue":"ACM Multimedia","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[van de Sande et al., 2011] Koen E. A. van de Sande, Jasper R. R. Uijlings, Theo Gevers, and Arnold W. M. Smeulders. Segmentation as selective search for object recognition. In ICCV, pages 1879-1886, 2011.","title":"Segmentation as selective search for object recognition","authors":"E A Koen, Van De Sande, R R Jasper, Theo Uijlings, Arnold W M Gevers, Smeulders","year":"2011","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Vicente et al., 2011] Sara Vicente, Carsten Rother, and Vladimir Kolmogorov. Object cosegmentation. In CVPR, pages 2217-2224, 2011.","title":"Object cosegmentation","authors":"Sara Vicente, Carsten Rother, Vladimir Kolmogorov","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wang et al., 2013] Fan Wang, Qixing Huang, and Leonidas J. Guibas. Image co-segmentation via con- sistent functional maps. In ICCV, pages 849-856, 2013.","title":"Image co-segmentation via consistent functional maps","authors":"Fan Wang, Qixing Huang, Leonidas J Guibas","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Winn et al., 2005] John M. Winn, Antonio Criminisi, and Thomas P. Minka. Object categorization by learned uni- versal visual dictionary. In ICCV, pages 1800-1807, 2005.","title":"Object categorization by learned universal visual dictionary","authors":"John M Winn, Antonio Criminisi, Thomas P Minka","year":"2005","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yuan et al., 2017] Ze-Huan Yuan, Tong Lu, and Yirui Wu. Deep-dense conditional random fields for object co- segmentation. In IJCAI, pages 3371-3377, 2017.","title":"Deep-dense conditional random fields for object cosegmentation","authors":"Ze-Huan Yuan, Tong Lu, Yirui Wu","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}