{"type":"ScholarlyArticle","title":"Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion","authors":[{"name":"Yupei Wang","slug":"yupei-wang","given":"Yupei","family":"Wang","affiliation":"CRIPAC , NLPR , Institute of Automation , Chinese Academy of Sciences; University of Chinese Academy of Sciences"},{"name":"Xin Zhao","slug":"xin-zhao","given":"Xin","family":"Zhao","affiliation":"CRIPAC , NLPR , Institute of Automation , Chinese Academy of Sciences; University of Chinese Academy of Sciences"},{"name":"Yin Li","slug":"yin-li","given":"Yin","family":"Li","affiliation":"Carnegie Mellon University"},{"name":"Xuecai Hu","slug":"xuecai-hu","given":"Xuecai","family":"Hu","affiliation":"CRIPAC , NLPR , Institute of Automation , Chinese Academy of Sciences; University of Science and Technology of China"},{"name":"Kaiqi Huang","slug":"kaiqi-huang","given":"Kaiqi","family":"Huang","affiliation":"CRIPAC , NLPR , Institute of Automation , Chinese Academy of Sciences; University of Chinese Academy of Sciences; CAS Center for Excellence in Brain Science and Intelligence Technology"}],"abstract":"Shadow detection is an important and challenging problem in computer vision. Recently, single image shadow detection had achieved major progress with the development of deep convolutional networks. However, existing methods are still vulnerable to background clutters, and often fail to capture the global context of an input image. These global contextual and semantic cues are essential for accurately localizing the shadow regions. Moreover, rich spatial details are required to segment shadow regions with precise shape. To this end, this paper presents a novel model characterized by a deeply supervised parallel fusion (DSPF) network and a densely cascaded learning scheme. The DSPF network achieves a comprehensive fusion of global semantic cues and local spatial details by multiple stacked parallel fusion branches, which are learned in a deeply supervised manner. Moreover, the densely cascaded learning scheme is employed to refine the spatial details. Our method is evaluated on two widely used shadow detection benchmarks. Experimental results show that our method outperforms state-of-the-arts by a large margin.","doi":"10.24963/ijcai.2018/140","url":"https://ijcai.org/proceedings/2018/140","pdf":"https://ijcai.org/proceedings/2018/0140.pdf","markdown":"https://ijcai.org/proceedings/2018/140.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/140","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":140,"pages":{"first":1007,"last":1013},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Computer Vision: Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Corina B. et al., 2011] Peter J. K. Corina B., Zoltan B., and Laszlo V. Shadow detection and removal from a single image. SSIP, 2011.","title":"Shadow detection and removal from a single image","authors":"J K Peter, B Corina, B Zoltan, V Laszlo","year":"2011","venue":"SSIP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ecins et al., 2014] Aleksandrs Ecins, Cornelia Fermuller, and Yiannis Aloimonos. Shadow free segmentation in still images using local density measure. In ICCP, 2014.","title":"Shadow free segmentation in still images using local density measure","authors":"Aleksandrs Ecins, Cornelia Fermuller, Yiannis Aloimonos","year":"2014","venue":"ICCP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Finlayson et al., 2006] Graham D. Finlayson, Steven D. Hordley, Cheng Lu, and Mark S. Drew. On the removal of shadows from images. TPAMI, 28(1), 2006.","title":"On the removal of shadows from images","authors":"Graham D Finlayson, Steven D Hordley, Cheng Lu, Mark S Drew","year":"2006","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Finlayson et al., 2009] Graham D. Finlayson, Mark S. Drew, and Cheng Lu. Entropy minimization for shadow removal. IJCV, 85(1), 2009.","title":"Entropy minimization for shadow removal","authors":"Graham D Finlayson, Mark S Drew, Cheng Lu","year":"2009","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Guo et al., 2011] Ruiqi Guo, Qieyun Dai, and Derek Hoiem. Single-image shadow detection and removal us- ing paired regions. In CVPR, 2011.","title":"Single-image shadow detection and removal using paired regions","authors":"Ruiqi Guo, Qieyun Dai, Derek Hoiem","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hou et al., 2017] Qibin Hou, Ming Ming Cheng, Xiao Wei Hu, Ali Borji, Zhuowen Tu, and Philip Torr. Deeply su- pervised salient object detection with short connections. In CVPR, 2017.","title":"Deeply supervised salient object detection with short connections","authors":"Hou","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hu et al., 2018] Xiaowei Hu, Lei Zhu, Chi Wing Fu, Jing Qin, and Pheng Ann Heng. Direction-aware spatial con- text features for shadow detection. In CVPR, 2018.","title":"Direction-aware spatial context features for shadow detection","authors":"Xiaowei Hu, Lei Zhu, Chi Wing Fu, Jing Qin, Pheng, Ann Heng","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Huang et al., 2017] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. Densely con- nected convolutional networks. In CVPR, 2017.","title":"Densely connected convolutional networks","authors":"Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q Weinberger","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jia et al., 2014] Yangqing Jia, Evan Shelhamer, Jeff Don- ahue, Sergey Karayev, Jonathan Long, Ross Girshick, Ser- gio Guadarrama, and Trevor Darrell. Caffe: Convolution- al architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014.","title":"Caffe: Convolutional architecture for fast feature embedding","authors":"Jia","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Karsch et al., 2011] Kevin Karsch, Varsha Hedau, David Forsyth, and Derek Hoiem. Rendering synthetic objects into legacy photographs. In SIGGRAPH Asia Conference, 2011.","title":"Rendering synthetic objects into legacy photographs","authors":"Kevin Karsch, Varsha Hedau, David Forsyth, Derek Hoiem","year":"2011","venue":"SIGGRAPH Asia Conference","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Khan et al., 2016] Salman H. Khan, Mohammed Ben- namoun, Ferdous Sohel, and Roberto Togneri. Automatic shadow detection and removal from a single image. TPA- MI, 2016.","title":"Automatic shadow detection and removal from a single image","authors":"Salman H Khan, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lalonde et al., 2010] Jean Francois Lalonde, Alexei A. E- fros, and Srinivasa G. Narasimhan. Estimating natural il- lumination from a single outdoor image. In ICCV, 2010.","title":"Estimating natural illumination from a single outdoor image","authors":"Jean Francois Lalonde, Alexei A Efros, Srinivasa G Narasimhan","year":"2010","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lee et al., 2015] Chen-Yu Lee, Saining Xie, Patrick Gal- lagher, Zhengyou Zhang, and Zhuowen Tu. Deeply- supervised nets. In AISTATS, volume 2, page 6, 2015.","title":"Deeplysupervised nets","authors":"Chen-Yu Lee, Saining Xie, Patrick Gallagher, Zhengyou Zhang, Zhuowen Tu","year":"2015","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2016] Ke Li, Bharath Hariharan, and Jitendra Ma- lik. Iterative instance segmentation. In CVPR, 2016.","title":"Iterative instance segmentation","authors":"Ke Li, Bharath Hariharan, Jitendra Malik","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nguyen et al., 2017] Vu Nguyen, Tomas F Yago Vicente, Maozheng Zhao, Minh Hoai, and Dimitris Samaras. Shad- ow detection with conditional generative adversarial net- works. In ICCV, 2017.","title":"Shadow detection with conditional generative adversarial networks","authors":"Tomas F Yago Vu Nguyen, Maozheng Vicente, Minh Zhao, Dimitris Hoai, Samaras","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Panagopoulos et al., 2012] Alexandros Panagopoulos, Chaohui Wang, Dimitris Samaras, and Nikos Paragios. Simultaneous cast shadows, illumination and geometry inference using hypergraphs. TPAMI, 35(2), 2012.","title":"Simultaneous cast shadows, illumination and geometry inference using hypergraphs","authors":"Alexandros Panagopoulos, Chaohui Wang, Dimitris Samaras, Nikos Paragios","year":"2012","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Peng et al., 2017] Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, and Jian Sun. Large kernel matters -im- prove semantic segmentation by global convolutional net- work. 2017.","title":"Large kernel matters -improve semantic segmentation by global convolutional network","authors":"Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pinheiro et al., 2016] Pedro O Pinheiro, Tsung-Yi Lin, Ro- nan Collobert, and Piotr Dollár. Learning to refine object segments. In ECCV, 2016.","title":"Learning to refine object segments","authors":"Tsung-Yi Pedro O Pinheiro, Ronan Lin, Piotr Collobert, Dollár","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Qu et al., 2017] Liangqiong Qu, Jiandong Tian, Shengfeng He, Yandong Tang, and Rynson W. H. Lau. Deshadownet: A multi-context embedding deep network for shadow re- moval. In CVPR, 2017.","title":"Deshadownet: A multi-context embedding deep network for shadow removal","authors":"Qu","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Shelhamer et al., 2017] Evan Shelhamer, Jonathan Long, and Trevor Darrell. Fully convolutional networks for se- mantic segmentation. TPAMI, 2017.","title":"Fully convolutional networks for semantic segmentation","authors":"Evan Shelhamer, Jonathan Long, Trevor Darrell","year":"2017","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arX- iv: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":23,"raw":"[Tu and Bai, 2010] Zhuowen Tu and Xiang Bai. Auto- context and its application to high-level vision tasks and 3d brain image segmentation. TPAMI, 2010.","title":"Zhuowen Tu and Xiang Bai. Autocontext and its application to high-level vision tasks and 3d brain image segmentation","authors":"Bai Tu","year":"2010","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tumblin and Williams, 2011] Jack Tumblin and Lance Williams. What characterizes a shadow boundary under the sun and sky? In ICCV, 2011.","title":"What characterizes a shadow boundary under the sun and sky?","authors":"Williams ; Tumblin, Jack Tumblin, Lance Williams","year":"2011","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Vicente et al., 2016] Tomás F Yago Vicente, Le Hou, Chen- Ping Yu, Minh Hoai, and Dimitris Samaras. Large-scale training of shadow detectors with noisily-annotated shad- ow examples. In ECCV. Springer, 2016.","title":"Large-scale training of shadow detectors with noisily-annotated shadow examples","authors":"Yago Tomás, Le Vicente, Chen-Ping Hou, Minh Yu, Dimitris Hoai, Samaras","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Vicente et al., 2018] Tomas F Yago Vicente, Minh Hoai, and Dimitris Samaras. Leave-one-out kernel optimization for shadow detection and removal. TPAMI, 2018.","title":"Leave-one-out kernel optimization for shadow detection and removal","authors":"Tomas F Yago Vicente, Minh Hoai, Dimitris Samaras","year":"2018","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2017a] Tiantian Wang, Ali Borji, Lihe Zhang, Pingping Zhang, and Huchuan Lu. A stagewise refinement model for detecting salient objects in images. In ICCV, 2017.","title":"A stagewise refinement model for detecting salient objects in images","authors":"Wang","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2017b] Yupei Wang, Xin Zhao, and Kaiqi Huang. Deep crisp boundaries. In CVPR, 2017.","title":"Deep crisp boundaries","authors":"Wang","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xie and Tu, 2015] Saining Xie and Zhuowen Tu. Holistically-nested edge detection. In ICCV, 2015.","title":"Holistically-nested edge detection","authors":"Tu ; Xie, Saining Xie, Zhuowen Tu","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2017] Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, and Ruan Xiang. Amulet: Aggregating multi-level convolutional features for salient object detec- tion. In ICCV, 2017.","title":"Amulet: Aggregating multi-level convolutional features for salient object detection","authors":"Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, Ruan Xiang","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhao et al., 2017] Hengshuang Zhao, Jianping Shi, Xiao- juan Qi, Xiaogang Wang, and Jiaya Jia. Pyramid scene parsing network. In CVPR, 2017.","title":"Pyramid scene parsing network","authors":"Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu et al., 2011] Jiejie Zhu, Kegan G. G. Samuel, Syed Z. Masood, and Marshall F. Tappen. Learning to recognize shadows in monochromatic natural images. In CVPR, 2011.","title":"Learning to recognize shadows in monochromatic natural images","authors":"Jiejie Zhu, G G Kegan, Samuel, Z Syed, Marshall F Masood, Tappen","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}