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 126–140 of 140 papers

TitleStatusHype
Self-Transfer Learning for Fully Weakly Supervised Object Localization—0
Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization—0
SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost—0
Towards Two-Stream Foveation-based Active Vision Learning—0
Training object class detectors with click supervision—0
Two-Phase Learning for Weakly Supervised Object Localization—0
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection—0
Weakly Supervised Localization Using Background Images—0
Weakly Supervised Object Localization and Detection: A Survey—0
Weakly Supervised Object Localization on grocery shelves using simple FCN and Synthetic Dataset—0
Weakly Supervised Object Localization Using Size Estimates—0
Weakly Supervised Object Localization Using Things and Stuff Transfer—0
Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning—0
Weakly Supervised Object Localization With Progressive Domain Adaptation—0
Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation—0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.