Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Tao, Zhang, Jie, Liu, Huashan, Wang, Zhijie, Pang, Shengyuan
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916636808708096
author Feng, Tao
Zhang, Jie
Liu, Huashan
Wang, Zhijie
Pang, Shengyuan
author_facet Feng, Tao
Zhang, Jie
Liu, Huashan
Wang, Zhijie
Pang, Shengyuan
contents Deep hashing retrieval has gained widespread use in big data retrieval due to its robust feature extraction and efficient hashing process. However, training advanced deep hashing models has become more expensive due to complex optimizations and large datasets. Coreset selection and Dataset Condensation lower overall training costs by reducing the volume of training data without significantly compromising model accuracy for classification task. In this paper, we explore the effect of mainstream dataset condensation methods for deep hashing retrieval and propose IEM (Information-intensive feature Embedding Matching), which is centered on distribution matching and incorporates model and data augmentation techniques to further enhance the feature of hashing space. Extensive experiments demonstrate the superior performance and efficiency of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2305_18076
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching
Feng, Tao
Zhang, Jie
Liu, Huashan
Wang, Zhijie
Pang, Shengyuan
Computer Vision and Pattern Recognition
Deep hashing retrieval has gained widespread use in big data retrieval due to its robust feature extraction and efficient hashing process. However, training advanced deep hashing models has become more expensive due to complex optimizations and large datasets. Coreset selection and Dataset Condensation lower overall training costs by reducing the volume of training data without significantly compromising model accuracy for classification task. In this paper, we explore the effect of mainstream dataset condensation methods for deep hashing retrieval and propose IEM (Information-intensive feature Embedding Matching), which is centered on distribution matching and incorporates model and data augmentation techniques to further enhance the feature of hashing space. Extensive experiments demonstrate the superior performance and efficiency of our approach.
title Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.18076