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 71–80 of 140 papers

TitleStatusHype
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label—0
Information Entropy Based Feature Pooling for Convolutional Neural Networks—0
Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learning—0
LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization—0
Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization—0
Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection—0
Learning Instance Activation Maps for Weakly Supervised Instance Segmentation—0
Leveraging Activations for Superpixel Explanations—0
LID 2020: The Learning from Imperfect Data Challenge Results—0
Location-free Human Pose Estimation—0
Show:102550
← PrevPage 8 of 14Next →

No leaderboard results yet.