Transductive Zero-shot Hashing Via Coarse-to-fine Similarity Mining

Abstract

Zero-shot Hashing (ZSH) is to learn hashing models for novel/target classes without training data, which is an important and challenging problem. Most existing ZSH approaches exploit transfer learning via an intermediate shared semantic representations between the seen/source classes and novel/target classes. However, due to having disjoint, the hash functions learned from the source dataset are biased when applied directly to the target classes. In this paper, we study the transductive ZSH, i.e., we have unlabeled data for novel classes. We put forward a simple yet efficient joint learning approach via coarse-to-fine similarity mining which transfers knowledges from source data to target data. It mainly consists of two building blocks in the proposed deep architecture: 1) a shared two-streams network, which the first stream operates on the source data and the second stream operates on the unlabeled data, to learn the effective common image representations, and 2) a coarse-to-fine modu

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keylai2017transductive

Related papers

• Transductive Zero-shot Hashing For Multilabel Image Retrieval (2019)8.82
• Cross-modal Zero-shot Hashing (2019)8.09
• Zero-shot Hashing Via Transferring Supervised Knowledge (2016)15.48
• Hashing In The Zero Shot Framework With Domain Adaptation (2017)10.21
• COMAE: Comprehensive Attribute Exploration For Zero-shot Hashing (2024)9.59
• Attribute-guided Network For Cross-modal Zero-shot Hashing (2018)13.93
• Information-theoretic Hashing For Zero-shot Cross-modal Retrieval (2022)0.00
• Deep Hashing: A Joint Approach For Image Signature Learning (2016)5.24