Concepthash: Interpretable Fine-grained Hashing Via Concept Discovery

Abstract

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves sub-code level interpretability. In ConceptHash, each sub-code corresponds to a human-understandable concept, such as an object part, and these concepts are automatically discovered without human annotations. Specifically, we leverage a Vision Transformer architecture and introduce concept tokens as visual prompts, along with image patch tokens as model inputs. Each concept is then mapped to a specific sub-code at the model output, providing natural sub-code interpretability. To capture subtle visual differences among highly similar sub-categories (e.g., bird species), we incorporate language guidance to ensure that the learned hash codes are distinguishable within fine-grained object classes while maintaining semantic alignment. This approach allows u

Stats

• citations0
• S2 citations—
• github stars6
• HF likes0
• heat score1.69
• arxiv keyng2024concepthash

Related papers

• Unsupervised Hashing With Semantic Concept Mining (2022)7.50
• Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88
• Image Hashing Via Cross-view Code Alignment In The Age Of Foundation Models (2025)0.00
• Hashing In The Zero Shot Framework With Domain Adaptation (2017)10.21
• Deep Collaborative Discrete Hashing With Semantic-invariant Structure (2019)8.09
• Attribute-aware Deep Hashing With Self-consistency For Large-scale Fine-grained Image Retrieval (2023)11.76
• Hyperbolic Hierarchical Contrastive Hashing (2022)10.97
• Simultaneous Region Localization And Hash Coding For Fine-grained Image Retrieval (2019)0.00