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 41–50 of 140 papers

TitleStatusHype
Evaluating Weakly Supervised Object Localization Methods RightCode1
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and DatasetsCode1
A Generic Visualization Approach for Convolutional Neural NetworksCode1
Exploring Foveation and Saccade for Improved Weakly-Supervised LocalizationCode1
F-CAM: Full Resolution Class Activation Maps via Guided Parametric UpscalingCode1
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
Density-Based Region Search with Arbitrary Shape for Object Localization—0
CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization—0
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label—0
Deep Self-Taught Learning for Weakly Supervised Object Localization—0
Show:102550
← PrevPage 5 of 14Next →

No leaderboard results yet.