SOTAVerified

Weakly-Supervised Semantic Segmentation

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 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 111–120 of 296 papers

TitleStatusHype
FPR: False Positive Rectification for Weakly Supervised Semantic SegmentationCode1
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak SupervisionCode1
Boundary-Enhanced Co-Training for Weakly Supervised Semantic SegmentationCode1
Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and ReconstructorCode1
Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization—0
Weakly-Supervised Semantic Segmentation of Ships Using Thermal Imagery—0
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic SegmentationCode2
Weakly Supervised Semantic Segmentation for Large-Scale Point CloudCode1
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation—0
ISIM: Iterative Self-Improved Model for Weakly Supervised SegmentationCode1
Show:102550
← PrevPage 12 of 30Next →

No leaderboard results yet.