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 251–260 of 296 papers

TitleStatusHype
Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation—0
Harvesting Information from Captions for Weakly Supervised Semantic Segmentation—0
Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic SegmentationCode0
Weakly Supervised Learning of Instance Segmentation with Inter-pixel RelationsCode1
Weakly Supervised Semantic Segmentation of Satellite Images—0
Fully Using Classifiers for Weakly Supervised Semantic Segmentation with Modified Cues—0
FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference—0
The effect of scene context on weakly supervised semantic segmentation—0
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic SegmentationCode0
Learning Segmentation Masks with the Independence Prior—0
Show:102550
← PrevPage 26 of 30Next →

No leaderboard results yet.