SOTAVerified

Weakly-Supervised Object Localization

Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 140 papers

TitleStatusHype
Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization—0
PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI LocalizationCode0
TeD-Loc: Text Distillation for Weakly Supervised Object LocalizationCode0
Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learning—0
Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained VideosCode0
Leveraging Activations for Superpixel Explanations—0
SE3D: A Framework For Saliency Method Evaluation In 3D ImagingCode0
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for HistologyCode0
A Realistic Protocol for Evaluation of Weakly Supervised Object LocalizationCode0
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label—0
Show:102550
← PrevPage 1 of 14Next →

No leaderboard results yet.