A Study on the Channel Expansion VAE for Content-Based Image Retrieval-Reference-Cited by-同舟云学术

A Study on the Channel Expansion VAE for Content-Based Image Retrieval

Published:2022-09-13 Issue:18 Volume:12 Page:9160
ISSN:2076-3417
Container-title:Applied Sciences
language:en
Short-container-title:Applied Sciences

Author:

Lee Kyounghak,Lee Yeonghun,Ko Hyung-Hwa,Kang Minsoo

Abstract

Content-based image retrieval (CBIR) focuses on video searching with fine-tuning of pre-trained off-the-shelf features. CBIR is an intuitive method for image retrieval, although it still requires labeled datasets for fine-tuning due to the inefficiency caused by annotation. Therefore, we explored an unsupervised model for feature extraction of image contents. We used a variational auto-encoder (VAE) expanding channel of neural networks and studied the activation of layer outputs. In this study, the channel expansion method boosted the capability of image retrieval by exploring more kernels and selecting a layer of comparatively activated object region. The experiment included a comparison of channel expansion and visualization of each layer in the encoder network. The proposed model achieved (52.7%) mAP, which outperformed (36.5%) the existing VAE on the MNIST dataset.

Funder

Kwangwoon University

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Link

https://www.mdpi.com/2076-3417/12/18/9160/pdf

Reference30 articles.

1. Criminal Investigation Image Retrieval Based on Deep Learning;Dongyuan;Proceedings of the 2020 International Conference on Computer Network, Electronic and Automation (ICCNEA),2020

2. Decomposing Normal and Abnormal Features of Medical Image for Content-based Image Retrieval;Kazuma;arXiv,2020

3. Metric-Learning based Deep Hashing Network for Content Based Retrieval of Remote Sensing Images;Subhankar;IEEE Geosci. Remote Sens. Lett.,2020

4. Deep Learning: A New Era in Bridging the Semantic Gap;Urszula,2018

5. CNN Features off-the-shelf: An Astounding Baseline for Recognition;Ali;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W),2014

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Semi-Supervised Variational Autoencoders for Out-of-Distribution Generation;Entropy;2023-12-14

2. Effective Information Guidance for Chinese Font Generation with Skeleton and Channel Expansion;2023 2nd International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR);2023-12-08

3. Experimental Comparison of Autoencoder Variants in Content-Based Image Retrieval;2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT);2023-07-06

4. A Novel Hybrid Approach for a Content-Based Image Retrieval Using Feature Fusion;Applied Sciences;2023-04-04