Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ono, Seitaro, Ogino, Yuka, Toizumi, Takahiro, Ito, Atsushi, Tsukada, Masato
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2401.06438
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912179381338112
author Ono, Seitaro
Ogino, Yuka
Toizumi, Takahiro
Ito, Atsushi
Tsukada, Masato
author_facet Ono, Seitaro
Ogino, Yuka
Toizumi, Takahiro
Ito, Atsushi
Tsukada, Masato
contents In recent years, significant progress has been made in image recognition technology based on deep neural networks. However, improving recognition performance under low-light conditions remains a significant challenge. This study addresses the enhancement of recognition model performance in low-light conditions. We propose an image-adaptive learnable module which apply appropriate image processing on input images and a hyperparameter predictor to forecast optimal parameters used in the module. Our proposed approach allows for the enhancement of recognition performance under low-light conditions by easily integrating as a front-end filter without the need to retrain existing recognition models designed for low-light conditions. Through experiments, our proposed method demonstrates its contribution to enhancing image recognition performance under low-light conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06438
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Module
Ono, Seitaro
Ogino, Yuka
Toizumi, Takahiro
Ito, Atsushi
Tsukada, Masato
Computer Vision and Pattern Recognition
In recent years, significant progress has been made in image recognition technology based on deep neural networks. However, improving recognition performance under low-light conditions remains a significant challenge. This study addresses the enhancement of recognition model performance in low-light conditions. We propose an image-adaptive learnable module which apply appropriate image processing on input images and a hyperparameter predictor to forecast optimal parameters used in the module. Our proposed approach allows for the enhancement of recognition performance under low-light conditions by easily integrating as a front-end filter without the need to retrain existing recognition models designed for low-light conditions. Through experiments, our proposed method demonstrates its contribution to enhancing image recognition performance under low-light conditions.
title Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Module
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.06438