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 51–60 of 65 papers

TitleStatusHype
On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning—0
Learning to Compose Soft Prompts for Compositional Zero-Shot LearningCode1
BatchFormer: Learning to Explore Sample Relationships for Robust Representation LearningCode2
3D Compositional Zero-shot Learning with DeCompositional Consensus—0
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators—0
Learning Single/Multi-Attribute of Object with Symmetry and GroupCode1
Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair RecognitionCode0
Independent Prototype Propagation for Zero-Shot CompositionalityCode0
Learning Graph Embeddings for Open World Compositional Zero-Shot LearningCode1
Learning Graph Embeddings for Compositional Zero-shot LearningCode1
Show:102550
← PrevPage 6 of 7Next →

No leaderboard results yet.