Article

Contextual Feature Expansion with Superordinate Concept for Compositional Zero-Shot Learning

2025-08-07

Abstract excerpt

Compositional Zero-Shot Learning (CZSL) seeks to enable machines to recognize objects and attributes (i.e.,primitives), learn their associations, and generalize to novel compositions, enabling systems to exhibit a human-like ability to infer and generalize. Existing approaches, multi-label and multi-class classification, face inherent trade-offs: the former suffers from biases against unrelated compositions, while...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 0587f4c9-b09a-5d5e-bd14-f5e9110c4ee6
DOI: 10.20944/preprints202508.0451.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Contextual Feature Expansion with Superordinate Concept for Compositional Zero-Shot LearningDOI 10.20944/preprints202508.0451.v1Read

Using Compositionality to Learn Many Categories from Few ExamplesSemantic proximity Read

Abstracted Gaussian Prototypes for One-Shot Concept LearningSemantic proximity Read

Meta-Learning for Real-World Class Incremental Learning: A Transformer-Based ApproachSemantic proximity Read

Unsupervised Few-shot Object Recognition by Self-Supervised TrainingSemantic proximity Read

Zero-shot learning of naturalistic concepts via conceptual systems alignmentSemantic proximity Read

Self-Supervised Learning Principles Challenges and Emerging DirectionsSemantic proximity Read

DiscoverNet: Unsupervised Video Object Discovery through Discrete Visual Tokenization and Language Model-Inspired ReconstructionSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

Towards Cognition-Aligned Visual Language Models via Zero-Shot Instance RetrievalSemantic proximity Read

Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract ConceptsSemantic proximity Read

System alignment supports cross-domain learning and zero-shot generalisationSemantic proximity Read

One Shot Cluster Based Approach for the Detection of COVID-19 from Chest X-Ray ImagesSemantic proximity Read