paper-with-me

홈 › Papers

Information-Theoretic Hashing for Zero-Shot Cross-Modal Retrieval

2022-09-26 · Yufeng Shi, Shujian Yu, Duanquan Xu, Xinge You

Zero-shot cross-modal retrieval (ZS-CMR) deals with the retrieval problem among heterogenous data from unseen classes. Typically, to guarantee generalization, the pre-defined class embeddings from natural language processing (NLP) models are used to build a common space. In this paper, instead of using an extra NLP model to define a common space beforehand, we consider a totally different way to construct (or learn) a common hamming space from an information-theoretic perspective. We term our model the Information-Theoretic Hashing (ITH), which is composed of two cascading modules: an Adaptive Information Aggregation (AIA) module; and a Semantic Preserving Encoding (SPE) module. Specifically, our AIA module takes the inspiration from the Principle of Relevant Information (PRI) to construct a common space that adaptively aggregates the intrinsic semantics of different modalities of data and filters out redundant or irrelevant information. On the other hand, our SPE module further generates the hashing codes of different modalities by preserving the similarity of intrinsic semantics with the element-wise Kullback-Leibler (KL) divergence. A total correlation regularization term is also imposed to reduce the redundancy amongst different dimensions of hash codes. Sufficient experiments on three benchmark datasets demonstrate the superiority of the proposed ITH in ZS-CMR. Source code is available in the supplementary material.

📄 PDF Abstract BibTeX arXiv:2209.12491

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Modal RetrievalRetrievalZero-Shot Cross-Modal Retrieval

Similar Papers 제목 키워드 기반

Cross-modal Zero-shot Hashing by Label Attributes Embedding

2021-11-07 · Runmin Wang, Guoxian Yu, Lei Liu, Lizhen Cui 외

Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search. Most CMH solutions ideally assume the labels of training and testing set are identical. However, the assu…

Attribute

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

2018-02-06 · Zhong Ji, Yuxin Sun, Yunlong Yu, Yanwei Pang 외

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 s…

AttributeCross-Modal RetrievalImage RetrievalRetrieval+1

Zero-Shot Sketch-Image Hashing

2018-03-06 · CVPR 2018 6 · Yuming Shen, Li Liu, Fumin Shen, Ling Shao

Recent studies show that large-scale sketch-based image retrieval (SBIR) can be efficiently tackled by cross-modal binary representation learning methods, where Hamming distance matching significantly speeds up the proce…

Image RetrievalRepresentation LearningRetrievalSketch-Based Image Retrieval

Cross-modal Zero-shot Hashing

2019-08-19 · Xuanwu Liu, Zhao Li, Jun Wang, Guoxian Yu 외

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 …

AttributeRetrieval

Zero-Shot Hashing Based on Reconstruction With Part Alignment

2025-03-10 · Yan Jiang, Zhongmiao Qi, Jianhao Li, Jiangbo Qian 외

Hashing algorithms have been widely used in large-scale image retrieval tasks, especially for seen class data. Zero-shot hashing algorithms have been proposed to handle unseen class data. The key technique in these algor…

AttributeImage Retrieval