数据集包含4447张原图及对应的ground truth图,每张图都按像素级别进行标注,用于显著性物体检测研究。
数据集包含4447张原图及对应的ground truth图,每张图都按像素级别进行标注,用于显著性物体检测研究。
数据示例:
引用:
Guanbin Li and Yizhou Yu, Deep Contrast Learning for Salient Object Detection, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016. [BibTex] (paper)
Guanbin Li and Yizhou Yu, Visual Saliency Detection Based on Multiscale Deep CNN Features, IEEE Transactions on Image Processing (TIP), Vol 25, No 11, pp.5012-5024, 2016. (paper)
Guanbin Li and Yizhou Yu, Visual Saliency Based on Multiscale Deep Features, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, June 2015. [BibTex] (paper | supplemental)
图片数量 | 4447 |
发布时间 | 2015年 |