Transductive Zero-shot Hashing For Multilabel Image Retrieval

Abstract

Hash coding has been widely used in approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zeor-shot hashing techniques have been studied. However, existing zeor-shot hashing methods focus on the retrieval of single-label images, and cannot handle multi-label images. In this paper, for the first time, a novel transductive zero-shot hashing method is proposed for multi-label unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data.

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keyzou2019transductive

Related papers

• Zero-shot Hashing Via Transferring Supervised Knowledge (2016)15.48
• Cross-modal Zero-shot Hashing (2019)8.09
• Hashing In The Zero Shot Framework With Domain Adaptation (2017)10.21
• Transductive Zero-shot Hashing Via Coarse-to-fine Similarity Mining (2017)5.84
• Hierarchy Neighborhood Discriminative Hashing For An Unified View Of Single-label And Multi-label Image Retrieval (2019)0.00
• Improved Deep Hashing With Soft Pairwise Similarity For Multi-label Image Retrieval (2018)16.82
• Information-theoretic Hashing For Zero-shot Cross-modal Retrieval (2022)0.00
• Attribute-guided Network For Cross-modal Zero-shot Hashing (2018)13.93