self adaptive
Recently Published Documents


TOTAL DOCUMENTS

6604
(FIVE YEARS 1504)

H-INDEX

85
(FIVE YEARS 17)

Nano Energy ◽  
2022 ◽  
Vol 93 ◽  
pp. 106805
Author(s):  
Zhiyuan Hu ◽  
Wei Deng ◽  
Bangyi He ◽  
Jianhua Liang ◽  
Xufeng Zhou ◽  
...  
Keyword(s):  

2022 ◽  
Vol 13 (1) ◽  
pp. 1-11
Author(s):  
Shih-Chia Huang ◽  
Quoc-Viet Hoang ◽  
Da-Wei Jaw

Despite the recent improvement of object detection techniques, many of them fail to detect objects in low-luminance images. The blurry and dimmed nature of low-luminance images results in the extraction of vague features and failure to detect objects. In addition, many existing object detection methods are based on models trained on both sufficient- and low-luminance images, which also negatively affect the feature extraction process and detection results. In this article, we propose a framework called Self-adaptive Feature Transformation Network (SFT-Net) to effectively detect objects in low-luminance conditions. The proposed SFT-Net consists of the following three modules: (1) feature transformation module, (2) self-adaptive module, and (3) object detection module. The purpose of the feature transformation module is to enhance the extracted feature through unsupervisely learning a feature domain projection procedure. The self-adaptive module is utilized as a probabilistic module producing appropriate features either from the transformed or the original features to further boost the performance and generalization ability of the proposed framework. Finally, the object detection module is designed to accurately detect objects in both low- and sufficient- luminance images by using the appropriate features produced by the self-adaptive module. The experimental results demonstrate that the proposed SFT-Net framework significantly outperforms the state-of-the-art object detection techniques, achieving an average precision (AP) of up to 6.35 and 11.89 higher on the sufficient- and low- luminance domain, respectively.


2022 ◽  
Vol 149 ◽  
pp. 106797
Author(s):  
Fang Song ◽  
Chuantao Zheng ◽  
Shuo Yang ◽  
Kaiyuan Zheng ◽  
Weilin Ye ◽  
...  

2022 ◽  
Vol 175 ◽  
pp. 121371
Author(s):  
Ni He ◽  
Wang Yongqiao ◽  
Jiang Tao ◽  
Chen Zhaoyu
Keyword(s):  

2022 ◽  
Vol 893 ◽  
pp. 162178
Author(s):  
Zhen Xu ◽  
Junlin Lu ◽  
Daobo Li ◽  
Dongmei Zhang ◽  
Dizi Yang ◽  
...  

Computing ◽  
2022 ◽  
Author(s):  
Hameed Khan ◽  
Kamal K. Kushwah ◽  
Muni Raj Maurya ◽  
Saurabh Singh ◽  
Prashant Jha ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document