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 51–60 of 140 papers

TitleStatusHype
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization—0
Learning Instance Activation Maps for Weakly Supervised Instance Segmentation—0
LID 2020: The Learning from Imperfect Data Challenge Results—0
Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization—0
Foreground Activation Maps for Weakly Supervised Object Localization—0
Hierarchical Complementary Learning for Weakly Supervised Object Localization—0
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization—0
How hard can it be? Estimating the difficulty of visual search in an image—0
Improved Techniques For Weakly-Supervised Object Localization—0
Fine-Grained Attention for Weakly Supervised Object Localization—0
Show:102550
← PrevPage 6 of 14Next →

No leaderboard results yet.