王兴刚

个人信息Personal Information

教授   博士生导师   硕士生导师  

性别:男

在职信息:在职

所在单位:电子信息与通信学院

学历:研究生(博士)毕业

学位:工学博士学位

毕业院校:华中科技大学

学科:通信与信息系统
信号与信息处理

DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection

点击次数:

论文类型:会议论文

第一作者:Shen,Wei

通讯作者:Bai,Xiang

合写作者:Zhang,Zhijiang,Yan,Wang,Xinggang

发表刊物:2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

发表时间:2015-06-07

摘要:Contour detection serves as the basis of a variety of computer vision tasks such as image segmentation and object recognition. The mainstream works to address this problem focus on designing engineered gradient features. In this work, we show that contour detection accuracy can be improved by instead making the use of the deep features learned from convolutional neural networks (CNNs). While rather than using the networks as a blackbox feature extractor, we customize the training strategy by partitioning contour (positive) data into subclasses and fitting each subclass by different model parameters. A new loss function, named positive-sharing loss, in which each subclass shares the loss for the whole positive class, is proposed to learn the parameters. Compared to the sofmax loss function, the proposed one, introduces an extra regularizer to emphasizes the losses for the positive and negative classes, which facilitates to explore more discriminative features. Our experimental results demonstrate that learned deep features can achieve top performance on Berkeley Segmentation Dataset and Benchmark (BSDS500) and obtain competitive cross dataset generalization result on the NYUD dataset.