{"type":"ScholarlyArticle","title":"DEL: Deep Embedding Learning for Efficient Image Segmentation","authors":[{"name":"Yun Liu","slug":"yun-liu","given":"Yun","family":"Liu","affiliation":"Nankai University"},{"name":"Peng-Tao Jiang","slug":"peng-tao-jiang","given":"Peng-Tao","family":"Jiang","affiliation":"Nankai University"},{"name":"Vahan Petrosyan","slug":"vahan-petrosyan","given":"Vahan","family":"Petrosyan","affiliation":"KTH Royal Institute of Technology"},{"name":"Shi-Jie Li","slug":"shi-jie-li","given":"Shi-Jie","family":"Li","affiliation":"Nankai University"},{"name":"Jiawang Bian","slug":"jiawang-bian","given":"Jiawang","family":"Bian","affiliation":"University of Adelaide"},{"name":"Le Zhang","slug":"le-zhang","given":"Le","family":"Zhang","affiliation":"Advanced Digital Sciences Center"},{"name":"Ming-Ming Cheng","slug":"ming-ming-cheng","given":"Ming-Ming","family":"Cheng","affiliation":"Nankai University"}],"abstract":"Image\r\nsegmentation has been explored for many years and still remains a\r\ncrucial vision problem. Some efficient or accurate segmentation\r\nalgorithms have been widely used in many vision applications.\r\nHowever, it is difficult to design a both efficient and accurate\r\nimage segmenter. In this paper, we propose a novel method called DEL\r\n(deep embedding learning) which can efficiently transform superpixels\r\ninto image segmentation. Starting with the SLIC superpixels, we train\r\na fully convolutional network to learn the feature embedding space\r\nfor each superpixel. The learned feature embedding corresponds to a\r\nsimilarity measure that measures the similarity between two adjacent\r\nsuperpixels. With the deep similarities, we can directly merge the\r\nsuperpixels into large segments. The evaluation results on BSDS500\r\nand PASCAL Context demonstrate that our approach achieves a good\r\ntrade-off between efficiency and effectiveness. Specifically, our DEL\r\nalgorithm can achieve comparable segments when compared with MCG but\r\nis much faster than it, i.e. 11.4fps vs. 0.07fps.","doi":"10.24963/ijcai.2018/120","url":"https://ijcai.org/proceedings/2018/120","pdf":"https://ijcai.org/proceedings/2018/0120.pdf","markdown":"https://ijcai.org/proceedings/2018/120.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/120","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":120,"pages":{"first":864,"last":870},"keywords":["Computer Vision: Computer Vision","Computer Vision: 2D and 3D Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Achanta et al., 2012] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk. SLIC superpixels compared to state-of-the- art superpixel methods. IEEE TPAMI, 34(11):2274-2282, 2012.","title":"SLIC superpixels compared to state-of-theart superpixel methods","authors":"Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, Sabine Süsstrunk","year":"2012","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Arbeláez et al., 2011] Pablo Arbeláez, Michael Maire, Charless Fowlkes, and Jitendra Malik. Contour detec- tion and hierarchical image segmentation. IEEE TPAMI, 33(5):898-916, 2011.","title":"Contour detection and hierarchical image segmentation","authors":"Arbeláez","year":"2011","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Arnab and Torr, 2017] Anurag Arnab and Philip HS Torr. Pixelwise instance segmentation with a dynamically in- stantiated network. In IEEE CVPR, pages 441-450, 2017.","title":"Pixelwise instance segmentation with a dynamically instantiated network","authors":"Anurag Arnab, Torr Philip","year":"2017","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2015a] Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. Se- mantic image segmentation with deep convolutional nets and fully connected CRFs. In ICLR, 2015.","title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","authors":"Chen","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2015b] Xiaozhi Chen, Huimin Ma, Xiang Wang, and Zhichen Zhao. Improving object proposals with multi-thresholding straddling expansion. In IEEE CVPR, pages 2587-2595, 2015.","title":"Improving object proposals with multi-thresholding straddling expansion","authors":"Chen","year":"2015","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheng et al., 2014] Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, and Philip Torr. BING: Binarized normed gradients for objectness estimation at 300fps. In IEEE CVPR, pages 3286-3293, 2014.","title":"BING: Binarized normed gradients for objectness estimation at 300fps","authors":"Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, Philip Torr","year":"2014","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cheng et al., 2016] Ming-Ming Cheng, Yun Liu, Qibin Hou, Jiawang Bian, Philip Torr, Shi-Min Hu, and Zhuowen Tu. HFS: Hierarchical feature selection for ef- ficient image segmentation. In ECCV, pages 867-882. Springer, 2016.","title":"HFS: Hierarchical feature selection for efficient image segmentation","authors":"Ming-Ming Cheng, Yun Liu, Qibin Hou, Jiawang Bian, Philip Torr, Shi-Min, Zhuowen Hu, Tu","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Comaniciu and Meer, 2002] Dorin Comaniciu and Peter Meer. Mean Shift: A robust approach toward feature space analysis. IEEE TPAMI, 24(5):603-619, 2002.","title":"Mean Shift: A robust approach toward feature space analysis","authors":"Dorin Comaniciu, Peter Meer","year":"2002","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cour et al., 2005] Timothee Cour, Florence Benezit, and Jianbo Shi. Spectral segmentation with multiscale graph decomposition. In IEEE CVPR, volume 2, pages 1124- 1131. IEEE, 2005.","title":"Spectral segmentation with multiscale graph decomposition","authors":"Timothee Cour, Florence Benezit, Jianbo Shi","year":"2005","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Everingham et al., 2007] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PAS- CAL Visual Object Classes Challenge 2007 (VOC2007) Results, 2007.","title":"The PAS-CAL Visual Object Classes Challenge","authors":"M Everingham, L Van Gool, C K I Williams, J Winn, A Zisserman","year":"2007","venue":"VOC2007) Results","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Farabet et al., 2013] Clement Farabet, Camille Couprie, Laurent Najman, and Yann LeCun. Learning hierarchi- cal features for scene labeling. IEEE TPAMI, 35(8):1915- 1929, 2013.","title":"Learning hierarchical features for scene labeling","authors":"Clement Farabet, Camille Couprie, Laurent Najman, Yann Lecun","year":"2013","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Felzenszwalb and Huttenlocher, 2004] Pedro F Felzen- szwalb and Daniel P Huttenlocher. Efficient graph-based image segmentation. IJCV, 59(2):167-181, 2004.","title":"Efficient graph-based image segmentation","authors":"F Pedro, Daniel P Felzenszwalb, Huttenlocher","year":"2004","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Girshick, 2015] Ross Girshick. Fast R-CNN. In IEEE ICCV, pages 1440-1448, 2015.","title":"Fast R-CNN","authors":"Ross Girshick","year":"2015","venue":"IEEE ICCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hariharan et al., 2011] Bharath Hariharan, Pablo Arbeláez, Lubomir Bourdev, Subhransu Maji, and Jitendra Malik. Semantic contours from inverse detectors. In IEEE ICCV, pages 991-998. IEEE, 2011.","title":"Semantic contours from inverse detectors","authors":"Bharath Hariharan, Pablo Arbeláez, Lubomir Bourdev, Subhransu Maji, Jitendra Malik","year":"2011","venue":"IEEE ICCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Juneja et al., 2013] Mayank Juneja, Andrea Vedaldi, CV Jawahar, and Andrew Zisserman. Blocks that shout: Distinctive parts for scene classification. In CVPR, pages 923-930, 2013.","title":"Blocks that shout: Distinctive parts for scene classification","authors":"Mayank Juneja, Andrea Vedaldi, Andrew Jawahar, Zisserman","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2016] Wei Liu, Andrew Rabinovich, and Alexan- der C Berg. ParseNet: Looking wider to see better. In ICLR, 2016.","title":"ParseNet: Looking wider to see better","authors":"Wei Liu, Andrew Rabinovich, Alexander C Berg","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2017] Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Kai Wang, and Xiang Bai. Richer convolutional features for edge detection. In IEEE CVPR, pages 3000-3009. IEEE, 2017.","title":"Richer convolutional features for edge detection","authors":"Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Kai Wang, Xiang Bai","year":"2017","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2018] Yun Liu, Ming-Ming Cheng, JiaWang Bian, Le Zhang, Peng-Tao Jiang, and Yang Cao. Seman- tic edge detection with diverse deep supervision. arXiv preprint arXiv:1804.02864, 2018.","title":"Semantic edge detection with diverse deep supervision","authors":"Yun Liu, Ming-Ming Cheng, Jiawang Bian, Le Zhang, Peng-Tao Jiang, Yang Cao","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mottaghi et al., 2014] Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fi- dler, Raquel Urtasun, and Alan Yuille. The role of context for object detection and semantic segmentation in the wild. In IEEE CVPR, pages 891-898, 2014.","title":"The role of context for object detection and semantic segmentation in the wild","authors":"Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, Alan Yuille","year":"2014","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pont-Tuset and Marques, 2016] Jordi Pont-Tuset and Fer- ran Marques. Supervised evaluation of image segmen- tation and object proposal techniques. IEEE TPAMI, 38(7):1465-1478, 2016.","title":"Jordi Pont-Tuset and Ferran Marques. Supervised evaluation of image segmentation and object proposal techniques","authors":"Pont-Tuset, Marques","year":"2016","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pont-Tuset et al., 2017] Jordi Pont-Tuset, Pablo Arbeláez, Jonathan T Barron, Ferran Marques, and Jitendra Ma- lik. Multiscale combinatorial grouping for image seg- mentation and object proposal generation. IEEE TPAMI, 39(1):128-140, 2017.","title":"Multiscale combinatorial grouping for image segmentation and object proposal generation","authors":"Jordi Pont-Tuset, Pablo Arbeláez, Jonathan T Barron, Ferran Marques, Jitendra Malik","year":"2017","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ren and Shakhnarovich, 2013] Zhile Ren and Gregory Shakhnarovich. Image segmentation by cascaded region agglomeration. In IEEE CVPR, pages 2011-2018, 2013.","title":"Zhile Ren and Gregory Shakhnarovich. Image segmentation by cascaded region agglomeration","authors":"Shakhnarovich Ren","year":"2013","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Ren et al., 2015] Carl Yuheng Ren, Victor Adrian Prisacariu, and Ian D Reid. gSLICr: SLIC super- pixels at over 250hz. arXiv preprint arXiv:1509.04232, 2015.","title":"gSLICr: SLIC superpixels at over 250hz","authors":"Carl Yuheng Ren, Adrian Victor, Ian D Prisacariu, Reid","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shi and Malik, 2000] Jianbo Shi and Jitendra Malik. Nor- malized cuts and image segmentation. IEEE TPAMI, 22(8):888-905, 2000.","title":"Normalized cuts and image segmentation","authors":"Jianbo Shi, Jitendra Malik","year":"2000","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Simonyan and Zisserman, 2014] K. Simonyan and A. Zis- serman. 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":"K Simonyan, A Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2011] Shu Wang, Huchuan Lu, Fan Yang, and Ming-Hsuan Yang. Superpixel tracking. In IEEE ICCV, pages 1323-1330. IEEE, 2011.","title":"Superpixel tracking","authors":"Shu Wang, Huchuan Lu, Fan Yang, Ming-Hsuan Yang","year":"2011","venue":"IEEE ICCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2017] Ziming Zhang, Yun Liu, Xi Chen, Yan- jun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, and Philip HS Torr. Sequential optimization for efficient high- quality object proposal generation. IEEE TPAMI, 2017.","title":"Sequential optimization for efficient highquality object proposal generation","authors":"Ziming Zhang, Yun Liu, Xi Chen, Yanjun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, Philip Hs Torr","year":"2017","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}