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 1–10 of 65 papers

TitleStatusHype
BatchFormer: Learning to Explore Sample Relationships for Robust Representation LearningCode2
MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot LearningCode1
Learning Clustering-based Prototypes for Compositional Zero-shot LearningCode1
Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot LearningCode1
Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language UnderstandingCode1
Learning Conditional Attributes for Compositional Zero-Shot LearningCode1
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot LearningCode1
Prompting Language-Informed Distribution for Compositional Zero-Shot LearningCode1
Learning Attention as Disentangler for Compositional Zero-shot LearningCode1
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot LearningCode1
Show:102550
← PrevPage 1 of 7Next →

No leaderboard results yet.