COMAE: Comprehensive Attribute Exploration For Zero-shot Hashing

Abstract

Zero-shot hashing (ZSH) has shown excellent success owing to its efficiency and generalization in large-scale retrieval scenarios. While considerable success has been achieved, there still exist urgent limitations. Existing works ignore the locality relationships of representations and attributes, which have effective transferability between seeable classes and unseeable classes. Also, the continuous-value attributes are not fully harnessed. In response, we conduct a COMprehensive Attribute Exploration for ZSH, named COMAE, which depicts the relationships from seen classes to unseen ones through three meticulously designed explorations, i.e., point-wise, pair-wise and class-wise consistency constraints. By regressing attributes from the proposed attribute prototype network, COMAE learns the local features that are relevant to the visual attributes. Then COMAE utilizes contrastive learning to comprehensively depict the context of attributes, rather than instance-independent optimization

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keyli2024comae

Related papers

• Attribute-guided Network For Cross-modal Zero-shot Hashing (2018)13.93
• Transductive Zero-shot Hashing Via Coarse-to-fine Similarity Mining (2017)5.84
• Cross-modal Zero-shot Hashing (2019)8.09
• Hashing In The Zero Shot Framework With Domain Adaptation (2017)10.21
• Zero-shot Hashing Via Transferring Supervised Knowledge (2016)15.48
• Transductive Zero-shot Hashing For Multilabel Image Retrieval (2019)8.82
• Information-theoretic Hashing For Zero-shot Cross-modal Retrieval (2022)0.00
• Attribute-aware Deep Hashing With Self-consistency For Large-scale Fine-grained Image Retrieval (2023)11.76