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 51–65 of 65 papers

TitleStatusHype
Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning—0
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning—0
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning—0
3D Compositional Zero-shot Learning with DeCompositional Consensus—0
Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair RecognitionCode0
Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot LearningCode0
Attention Based Simple Primitives for Open World Compositional Zero-Shot LearningCode0
Learning Invariant Visual Representations for Compositional Zero-Shot LearningCode0
GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot LearningCode0
Unified Framework for Open-World Compositional Zero-shot LearningCode0
Independent Prototype Propagation for Zero-Shot CompositionalityCode0
Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot LearningCode0
Hierarchical Visual Primitive Experts for Compositional Zero-Shot LearningCode0
Attributes as Operators: Factorizing Unseen Attribute-Object CompositionsCode0
Reference-Limited Compositional Zero-Shot LearningCode0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.