KinD-LCE Curve Estimation And Retinex Fusion On Low-Light Image

no code implementations • 19 Jul 2022 • Xiaochun Lei, Weiliang Mai, Junlin Xie, He Liu, Zetao Jiang, Zhaoting Gong, Chang Lu, Linjun Lu

The proposed method, KinD-LCE, uses a light curve estimation module to enhance the illumination map in the Retinex decomposed image, improving the overall image brightness.

Instance Segmentation object-detection +4

STDC-MA Network for Semantic Segmentation

no code implementations • 10 May 2022 • Xiaochun Lei, Linjun Lu, Zetao Jiang, Zhaoting Gong, Chang Lu, Jiaming Liang

Through this relationship, regions receiving much attention are integrated into the segmentation results, thereby reducing the unfocused regions of the input image and improving the effective utilization of multiscale features.

Autonomous Driving Segmentation +1

Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector

no code implementations • 10 May 2022 • Xiaochun Lei, Chang Lu, Zetao Jiang, Zhaoting Gong, Xiang Cai, Linjun Lu

Deep neural networks (DNNs) are vulnerable to adversarial attacks.

Object

Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN

no code implementations • 2 Sep 2021 • Yongsong Huang, Zetao Jiang, Qingzhong Wang, Qi Jiang, Guoming Pang

Recently, deep learning methods have dominated image super-resolution and achieved remarkable performance on visible images; however, IR images have received less attention.

Image Super-Resolution Infrared image super-resolution