Weakly-Supervised Semantic Segmentation
0 订阅
The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations thatare relatively easy to obtain, such as tags/labels of objects present in the image. Source: [Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf)
相关学科： Weakly supervised segmentationSemi-Supervised Semantic SegmentationSemantic SegmentationObject LocalizationSGANMulti-Label Image ClassificationMixupSuperpixelsAdaptive Robust LossFCN
学科讨论
暂无讨论内容，你可以
推荐文献
按被引用数
学科管理组
暂无学科课代表，你可以申请成为课代表
重要学者
Luc Van Gool
91399 被引用，1409
篇论文
Cordelia Schmid
82310 被引用，551
篇论文
Ming-Hsuan Yang
61951 被引用，641
篇论文
Shuicheng Yan
53033 被引用，825
篇论文
Mubarak Shah
45960 被引用，624
篇论文
Philip H. S. Torr
40625 被引用，589
篇论文
Tieniu Tan
32493 被引用，687
篇论文
Roberto Cipolla
32384 被引用，504
篇论文
Honglak Lee
31296 被引用，272
篇论文
Liang Wang
29105 被引用，684
篇论文