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 231–240 of 296 papers

TitleStatusHype
CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation—0
SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost—0
A Weakly-Supervised Semantic Segmentation Approach based on the Centroid Loss: Application to Quality Control and Inspection—0
Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images—0
WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma—0
Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation—0
The effect of scene context on weakly supervised semantic segmentation—0
CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation—0
CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics—0
ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images—0
Show:102550
← PrevPage 24 of 30Next →

No leaderboard results yet.