computer-vision-10
Weakly-Supervised Semantic Segmentation
3260 papers • 126 benchmarks • 313 datasets
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 that are relatively easy to obtain, such as tags/labels of objects present in the image. ( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in weakly-supervised-semantic-segmentation-10
Trend
Dataset
Best Model
Actions
PASCAL VOC 2012 val
PASCAL VOC 2012 val
PASCAL VOC 2012 test
PASCAL VOC 2012 test
Libraries
iUse these libraries to find weakly-supervised-semantic-segmentation-10 models and implementations
2 papers 181
Datasets
Subtasks
No subtasks available.
Most implemented papers
Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations
Sunghyun Cho, Suha Kwak, Jiwoon Ahn•Tue Apr 09 2019
IRNet is proposed, which estimates rough areas of individual instances and detects boundaries between different object classes and enables to assign instance labels to the seeds and to propagate them within the boundaries so that the entire areas of instances can be estimated accurately.
618
