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
DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning—0
Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning—0
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning—0
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning—0
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning—0
Learning Attention Propagation for Compositional Zero-Shot Learning—0
Reference-Limited Compositional Zero-Shot LearningCode0
Learning Invariant Visual Representations for Compositional Zero-Shot LearningCode0
On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning—0
3D Compositional Zero-shot Learning with DeCompositional Consensus—0
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators—0
Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair RecognitionCode0
Independent Prototype Propagation for Zero-Shot CompositionalityCode0
Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition—0
Attributes as Operators: Factorizing Unseen Attribute-Object CompositionsCode0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.