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 111–120 of 140 papers

TitleStatusHype
Learning Instance Activation Maps for Weakly Supervised Instance Segmentation—0
Compression and Localization in Reinforcement Learning for ATARI Games—0
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object DetectionCode0
Modularized Textual Grounding for Counterfactual ResilienceCode0
Min-Entropy Latent Model for Weakly Supervised Object DetectionCode0
Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic VideosCode0
ML-LocNet: Improving Object Localization with Multi-view Learning Network—0
Self-produced Guidance for Weakly-supervised Object LocalizationCode0
Adversarial Complementary Learning for Weakly Supervised Object LocalizationCode0
Weakly Supervised Object Localization on grocery shelves using simple FCN and Synthetic Dataset—0
Show:102550
← PrevPage 12 of 14Next →

No leaderboard results yet.