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 241–250 of 296 papers

TitleStatusHype
Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation—0
Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP—0
Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models—0
Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation—0
Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels—0
Causal Intervention for Weakly-Supervised Semantic Segmentation—0
Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation—0
Two-Phase Learning for Weakly Supervised Object Localization—0
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation—0
Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation—0
Show:102550
← PrevPage 25 of 30Next →

No leaderboard results yet.