{"type":"ScholarlyArticle","title":"Deep-dense Conditional Random Fields for Object Co-segmentation","authors":[{"name":"Zehuan Yuan","slug":"zehuan-yuan","given":"Zehuan","family":"Yuan","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Tong Lu","slug":"tong-lu","given":"Tong","family":"Lu","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Yirui Wu","slug":"yirui-wu","given":"Yirui","family":"Wu","affiliation":"College of Computer and Information , Hohai University , China"}],"abstract":"We address the problem of object co-segmentation in images. Object co-segmentation aims to segment common objects in images and has promising applications in AI agents. We solve it by proposing a co-occurrence map, which measures how likely an image region belongs to an object and also appears in other images. The co-occurrence map of an image is calculated by combining two parts: objectness scores of image regions and similarity evidences from object proposals across images. We introduce a deep-dense conditional random field framework to infer co-occurrence maps. Both similarity metric and objectness measure are learned end-to-end in a single deep network. We evaluate our method on two benchmarks and achieve competitive performance.","doi":"10.24963/ijcai.2017/471","url":"https://ijcai.org/proceedings/2017/471","pdf":"https://ijcai.org/proceedings/2017/0471.pdf","markdown":"https://ijcai.org/proceedings/2017/471.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/471","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":471,"pages":{"first":3371,"last":3377},"keywords":["Machine Learning: Learning Graphical Models","Machine Learning: Deep Learning","Robotics and Vision: Vision and Perception"],"videos":[],"references":[{"position":1,"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 The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, 13-18 June 2010, 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":"The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bengio, 2009] Yoshua Bengio. Learning deep architectures for AI. Foundations and Trends in Machine Learning, 2(1):1-127, 2009.","title":"Learning deep architectures for AI","authors":"Yoshua Bengio","year":"2009","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dai et al., 2013] Jifeng Dai, Ying Nian Wu, Jie Zhou, and Song-Chun Zhu. Cosegmentation and cosketch by unsu- pervised learning. In ICCV, 2013.","title":"Cosegmentation and cosketch by unsupervised learning","authors":"Jifeng Dai, Ying Nian Wu, Jie Zhou, Song-Chun Zhu","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"Everingham et al., ] Mark Everingham, Luc J. Van Gool, Christopher K. I. Williams, John M. Winn, and Andrew Zisserman. The pascal visual object classes (VOC) chal- lenge 2012.","title":"The pascal visual object classes (VOC) challenge","authors":"Everingham","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Faktor and Irani, 2013] Alon Faktor and Michal Irani. Co- segmentation by composition. In ICCV, 2013.","title":"Cosegmentation by composition","authors":"Alon Faktor, Michal Irani","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hayder et al., 2016] Zeeshan Hayder, Xuming He, and Mathieu Salzmann. Learning to co-generate object pro- posals with a deep structured network. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pages 2565-2573, 2016.","title":"Learning to co-generate object proposals with a deep structured network","authors":"Zeeshan Hayder, Xuming He, Mathieu Salzmann","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Jerripothula et al., 2016] Koteswar Rao Jerripothula, Jian- fei Cai, and Junsong Yuan. Image co-segmentation via saliency co-fusion. IEEE Trans. Multimedia, 18(9):1896- 1909, 2016.","title":"Image co-segmentation via saliency co-fusion","authors":"Koteswar Rao, Jerripothula, Jianfei Cai, Junsong Yuan","year":"2016","venue":"IEEE Trans. Multimedia","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Joulin et al., 2012] Armand Joulin, Francis Bach, and Jean Ponce. Multi-class cosegmentation. In CVPR, pages 542- 549, 2012.","title":"Multi-class cosegmentation","authors":"Armand Joulin, Francis Bach, Jean Ponce","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kim and Xing, 2012] Gunhee Kim and Eric P. Xing. On multiple foreground cosegmentation. In CVPR, pages 837-844, 2012.","title":"On multiple foreground cosegmentation","authors":"Xing ; ] Gunhee Kim, Eric P Kim, Xing","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Krähenbühl and Koltun, 2012] Philipp Krähenbühl and Vladlen Koltun. Efficient inference in fully connected crfs with gaussian edge potentials. CoRR, abs/1210.5644, 2012.","title":"Philipp Krähenbühl and Vladlen Koltun. Efficient inference in fully connected crfs with gaussian edge potentials","authors":"Koltun Krähenbühl","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Krähenbühl and Koltun, 2013] Philipp Krähenbühl and Vladlen Koltun. Parameter learning and convergent infer- ence for dense random fields. In ICML, pages 513-521, 2013.","title":"Philipp Krähenbühl and Vladlen Koltun. Parameter learning and convergent inference for dense random fields","authors":"Koltun Krähenbühl","year":"2013","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":12,"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":13,"raw":"[Ma and Latecki, 2013] Tianyang Ma and Longin Jan Late- cki. Graph transduction learning with connectivity con- straints with application to multiple foreground cosegmen- tation. In CVPR, pages 1955-1962, 2013.","title":"Tianyang Ma and Longin Jan Latecki. Graph transduction learning with connectivity constraints with application to multiple foreground cosegmentation","authors":"Latecki Ma","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mukherjee et al., 2011] Lopamudra Mukherjee, Vikas Singh, and Jiming Peng. Scale invariant cosegmentation for image groups. In CVPR, pages 1881-1888, 2011.","title":"Scale invariant cosegmentation for image groups","authors":"Lopamudra Mukherjee, Vikas Singh, Jiming Peng","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pinheiro et al., 2015] Pedro H. O. Pinheiro, Ronan Col- lobert, and Piotr Dollár. Learning to segment object candi- dates. In Advances in Neural Information Processing Sys- tems 28: Annual Conference on Neural Information Pro- cessing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pages 1990-1998, 2015.","title":"Learning to segment object candidates","authors":"H O Pedro, Ronan Pinheiro, Piotr Collobert, Dollár","year":"2015","venue":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Quan et al., 2016] Rong Quan, Junwei Han, Dingwen Zhang, and Feiping Nie. Object co-segmentation via graph optimized-flexible manifold ranking. In CVPR, pages 687-695, 2016.","title":"Object co-segmentation via graph optimized-flexible manifold ranking","authors":"Rong Quan, Junwei Han, Dingwen Zhang, Feiping Nie","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ren et al., 2015] Shaoqing Ren, Kaiming He, Ross B. Gir- shick, and Jian Sun. Faster R-CNN: towards real-time object detection with region proposal networks. In NIPS, pages 91-99, 2015.","title":"Faster R-CNN: towards real-time object detection with region proposal networks","authors":"Ren","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rubinstein et al., 2013] Michael Rubinstein, Armand Joulin, Johannes Kopf, and Ce Liu. Unsupervised joint object discovery and segmentation in internet images. In CVPR, pages 1939-1946, 2013.","title":"Unsupervised joint object discovery and segmentation in internet images","authors":"Michael Rubinstein, Armand Joulin, Johannes Kopf, Ce Liu","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rubio et al., 2012] José C. Rubio, Joan Serrat, Anto- nio M. López, and Nikos Paragios. Unsupervised co- segmentation through region matching. In CVPR, pages 749-756, 2012.","title":"Unsupervised cosegmentation through region matching","authors":"C José, Joan Rubio, Antonio M Serrat, Nikos López, Paragios","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tsai et al., 2016] Yi-Hsuan Tsai, Guangyu Zhong, and Ming-Hsuan Yang. Semantic co-segmentation in videos. In ECCV, pages 760-775, 2016.","title":"Semantic co-segmentation in videos","authors":"Yi-Hsuan Tsai, Guangyu Zhong, Ming-Hsuan Yang","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":22,"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":23,"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":24,"raw":"[Wang et al., 2013] Fan Wang, Qixing Huang, and Leonidas J. Guibas. Image co-segmentation via con- sistent functional maps. In ICCV, 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":25,"raw":"[Wu et al., 2016] Chenxia Wu, Jiemi Zhang, Ashutosh Sax- ena, and Silvio Savarese. Human centred object co- segmentation. CoRR, abs/1606.03774, 2016.","title":"Human centred object cosegmentation","authors":"Wu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yuan et al., 2014] Ze-Huan Yuan, Tong Lu, and Palaiah- nakote Shivakumara. A novel topic-level random walk framework for scene image co-segmentation. In ECCV, pages 695-709, 2014.","title":"A novel topic-level random walk framework for scene image co-segmentation","authors":"Ze-Huan Yuan, Tong Lu, Palaiahnakote Shivakumara","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2015] Dingwen Zhang, Junwei Han, Chao Li, and Jingdong Wang. Co-saliency detection via looking deep and wide. In CVPR, pages 2994-3002, 2015.","title":"Co-saliency detection via looking deep and wide","authors":"Zhang","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}