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 61–70 of 140 papers

TitleStatusHype
Self-produced Guidance for Weakly-supervised Object LocalizationCode0
Modularized Textual Grounding for Counterfactual ResilienceCode0
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Expeditious Saliency-guided Mix-up through Random Gradient ThresholdingCode0
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object DetectionCode0
DAP: Detection-Aware Pre-training with Weak SupervisionCode0
Soft Proposal Networks for Weakly Supervised Object LocalizationCode0
Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for HistologyCode0
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and SegmentationCode0
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object LocalizationCode0
Show:102550
← PrevPage 7 of 14Next →

No leaderboard results yet.