Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining

Lai, Hanjiang

doi:10.1145/3206025.3206026

Cited by 8 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, they leverage the hash codes to capture the semantic similarity relationship in a transferable semantic embedding space and propose a center regularization loss to preserve both intraconcept similarity and inter-concept distance. In addition, under the transductive setting [25], [26], Lai et al [27] propose a transductive zero-shot hashing method via coarse-to-fine similarity mining. In this way, a greedy binary classification network is first used to detect the most informative images from unseen category images.…”

Section: B Zero-shot Hashingmentioning

confidence: 99%

Attribute-Guided Network for Cross-Modal Zero-Shot Hashing

Sun

et al. 2020

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Zero-Shot Hashing aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achieved by utilizing a semantic embedding space to transfer knowledge from seen domain to unseen domain. Existing efforts mainly focus on single-modal retrieval task, especially Image-Based Image Retrieval (IBIR). However, as a highlighted research topic in the field of hashing, cross-modal retrieval is more common in real world applications. To address the Cross-Modal Zero-Shot Hashing (CMZSH) retrieval task, we propose a novel Attribute-Guided Network (AgNet), which can perform not only IBIR, but also Text-Based Image Retrieval (TBIR). In particular, AgNet aligns different modal data into a semantically rich attribute space, which bridges the gap caused by modality heterogeneity and zero-shot setting. We also design an effective strategy that exploits the attribute to guide the generation of hash codes for image and text within the same network. Extensive experimental results on three benchmark datasets (AwA, SUN, and ImageNet) demonstrate the superiority of AgNet on both cross-modal and single-modal zero-shot image retrieval tasks.

show abstract

Section: B Zero-shot Hashingmentioning

confidence: 99%

Attribute-Guided Network for Cross-Modal Zero-Shot Hashing

Sun

et al. 2020

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…To narrow the domain gap between seen data and unseen data, ZSH-DA [25] first learns a zero-shot hashing model on seen data, and then learns the final hashing model with a domain-adaptation algorithm. In [26], a transductive zeroshot hashing network (TZSH) was proposed, which contains a coarse-to-fine similarity mining to find most presentative target examples of each unseen labels, and adds these presentative examples and its corresponding predicted labels to the process of supervised hashing learning.…”

Section: Related Workmentioning

confidence: 99%

“…We compare our method (T-MLZSH) with several stateof-the-art hashing methods, including KSH [2], SDH [4], IMH [3], DHN [18], ZSH-DA [25], ZSH [23], TZSH [26]. Among these comparison methods, KSH and SDH are two typical supervised methods, IMH is one of the most representative unsupervised hashing methods, DHN is a deep learningbased supervised methods, ZSH-DA and ZSH are two zeroshot hashing methods, and TZSH is a transductive zero-shot hashing method.…”

Section: B Implementation Detailsmentioning

confidence: 99%

Transductive Zero-Shot Hashing for Multilabel Image Retrieval

Zou,

Zhang,

Cao

et al. 2019

Preprint

View full text Add to dashboard Cite

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 zeroshot 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. Extensive evaluations on three popular multi-label datasets demonstrate that, the proposed hashing method achieves significantly better results than the competing methods.

show abstract

“…ZSH aims to encode samples of unseen categories with the hash functions trained using only samples of seen categories, and by leveraging the techniques of supervised hashing and ZSL. Although ZSH methods [15], [18], [19], [20] achieve an impressive performance, they still have some limitations. They only focus on data with one modality, where both the query and the retrieval sets are in the same modality.…”

Section: Introductionmentioning

confidence: 99%

Cross-Modal Zero-Shot Hashing

Liu

Zhao

Wang

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.

show abstract

Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining

Cited by 8 publications

References 30 publications

Attribute-Guided Network for Cross-Modal Zero-Shot Hashing

Attribute-Guided Network for Cross-Modal Zero-Shot Hashing

Transductive Zero-Shot Hashing for Multilabel Image Retrieval

Cross-Modal Zero-Shot Hashing

Contact Info

Product

Resources

About