SOTAVerified

Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) is a computer vision task in which the goal is to recognize unseen compositions fromed from seen state and object during training. The key challenge in CZSL is the inherent entanglement between the state and object within the context of an image. Some example benchmarks for this task are MIT-states, UT-Zappos, and C-GQA. Models are usually evaluated with the Accuracy for both seen and unseen compositions, as well as their Harmonic Mean(HM).

( Image credit: Heosuab )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 31–40 of 65 papers

TitleStatusHype
Hierarchical Visual Primitive Experts for Compositional Zero-Shot LearningCode0
Reference-Limited Compositional Zero-Shot LearningCode0
3D Compositional Zero-shot Learning with DeCompositional Consensus—0
Visual Adaptive Prompting for Compositional Zero-Shot Learning—0
Anticipating Future Object Compositions without Forgetting—0
Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning—0
Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning—0
Compositional Zero-Shot Learning for Attribute-Based Object Reference in Human-Robot Interaction—0
Compositional Zero-shot Learning via Progressive Language-based Observations—0
Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition—0
Show:102550
← PrevPage 4 of 7Next →

No leaderboard results yet.