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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–65 of 65 papers

Title	Date	Tasks	Status
Feasibility with Language Models for Open-World Compositional Zero-Shot Learning	May 16, 2025	AttributeCompositional Zero-Shot Learning	—Unverified
Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning	Aug 30, 2024	AttributeCompositional Zero-Shot Learning	—Unverified
HOMOE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts	Nov 23, 2023	Compositional Zero-Shot LearningMixture-of-Experts	—Unverified
Learning Attention Propagation for Compositional Zero-Shot Learning	Oct 20, 2022	Compositional Zero-Shot LearningZero-Shot Learning	—Unverified
Learning Primitive Relations for Compositional Zero-Shot Learning	Jan 24, 2025	Compositional Zero-Shot LearningZero-Shot Learning	—Unverified
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators	Oct 22, 2021	Compositional Zero-Shot Learningimage-classification	—Unverified
LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning	Jan 1, 2025	AttributeCompositional Zero-Shot Learning	—Unverified
MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning	Jun 18, 2024	AttributeCompositional Zero-Shot Learning	—Unverified
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning	Nov 19, 2022	Compositional Zero-Shot LearningInductive Bias	—Unverified
On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning	Apr 23, 2022	Compositional Zero-Shot LearningImage Retrieval	—Unverified
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning	Nov 19, 2022	Compositional Zero-Shot LearningObject	—Unverified
Prompt Tuning for Zero-shot Compositional Learning	Dec 2, 2023	Common Sense ReasoningCompositional Zero-Shot Learning	—Unverified
Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning	Jan 22, 2025	AttributeCompositional Zero-Shot Learning	—Unverified
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning	Nov 5, 2022	Compositional Zero-Shot LearningDisentanglement	—Unverified
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning	Aug 16, 2024	Compositional Zero-Shot LearningZero-Shot Learning	—Unverified

Show:10 25 50

← PrevPage 3 of 3Next →

No leaderboard results yet.