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
Adversarial Complementary Learning for Weakly Supervised Object LocalizationCode0
DANet: Divergent Activation for Weakly Supervised Object LocalizationCode0
Soft Proposal Networks for Weakly Supervised Object LocalizationCode0
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for HistologyCode0
Convolutional STN for Weakly Supervised Object LocalizationCode0
Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained VideosCode0
Min-Entropy Latent Model for Weakly Supervised Object DetectionCode0
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and SegmentationCode0
Strengthen Learning Tolerance for Weakly Supervised Object LocalizationCode0
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised LocalizationCode0
Show:102550
← PrevPage 12 of 14Next →

No leaderboard results yet.