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
Background-aware Classification Activation Map for Weakly Supervised Object LocalizationCode0
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object LocalizationCode0
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Attributional Robustness Training using Input-Gradient Spatial AlignmentCode0
Knowledge-guided Causal Intervention for Weakly-supervised Object LocalizationCode0
PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI LocalizationCode0
Adversarial Normalization: I Can Visualize Everything (ICE)Code0
Progressive Representation Adaptation for Weakly Supervised Object LocalizationCode0
A Realistic Protocol for Evaluation of Weakly Supervised Object LocalizationCode0
Expeditious Saliency-guided Mix-up through Random Gradient ThresholdingCode0
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object LocalizationCode0
Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement MapsCode0
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information EstimatorCode0
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object DetectionCode0
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A SurveyCode0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.