SOTAVerified

Generalized Zero-Shot Learning

In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–161 of 161 papers

TitleStatusHype
PROTOtypical Logic Tensor Networks (PROTO-LTN) for Zero Shot LearningCode0
A Gating Model for Bias Calibration in Generalized Zero-shot LearningCode0
Data-Free Generalized Zero-Shot LearningCode0
Less but Better: Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM SemanticsCode0
A Meta-Learning Framework for Generalized Zero-Shot LearningCode0
Data Distribution Distilled Generative Model for Generalized Zero-Shot RecognitionCode0
Closed-form Sample Probing for Learning Generative Models in Zero-shot LearningCode0
Leveraging the Invariant Side of Generative Zero-Shot LearningCode0
CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned RepresentationCode0
Recognition of Unseen Bird Species by Learning from Field GuidesCode0
A Deep Dive into Adversarial Robustness in Zero-Shot LearningCode0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.