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
LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning—0
Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training—0
Unified Framework for Open-World Compositional Zero-shot LearningCode0
Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning—0
Cross-composition Feature Disentanglement for Compositional Zero-shot Learning—0
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning—0
Attention Based Simple Primitives for Open World Compositional Zero-Shot LearningCode0
Anticipating Future Object Compositions without Forgetting—0
Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot LearningCode0
MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning—0
Show:102550
← PrevPage 4 of 7Next →

No leaderboard results yet.