Výsledky vyhledávání

Report

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

Autor: Lei, Xiaochun, Mai, Weiliang, Xie, Junlin, Liu, He, Jiang, Zetao, Gong, Zhaoting, Lu, Chang, Lu, Linjun

Low-light images often suffer from noise and color distortion. Object detection, semantic segmentation, instance segmentation, and other tasks are challenging when working with low-light images because of image noise and chromatic aberration. We also

Externí odkaz: http://arxiv.org/abs/2207.09210

Zobrazit plný text záznamu

Report

STDC-MA Network for Semantic Segmentation

Autor: Lei, Xiaochun, Lu, Linjun, Jiang, Zetao, Gong, Zhaoting, Lu, Chang, Liang, Jiaming

Semantic segmentation is applied extensively in autonomous driving and intelligent transportation with methods that highly demand spatial and semantic information. Here, an STDC-MA network is proposed to meet these demands. First, the STDC-Seg struct

Externí odkaz: http://arxiv.org/abs/2205.04639

Zobrazit plný text záznamu

Report

Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector

Autor: Lei, Xiaochun, Lu, Chang, Jiang, Zetao, Gong, Zhaoting, Cai, Xiang, Lu, Linjun

Deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, object detectors may be attacked by applying a particular adversarial patch to the image. However, because the patch shrinks during preprocessing, most existing approac

Externí odkaz: http://arxiv.org/abs/2205.04638

Zobrazit plný text záznamu

Report

Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN

Autor: Huang, Yongsong, Jiang, Zetao, Wang, Qingzhong, Jiang, Qi, Pang, Guoming

Image super-resolution is important in many fields, such as surveillance and remote sensing. However, infrared (IR) images normally have low resolution since the optical equipment is relatively expensive. Recently, deep learning methods have dominate

Externí odkaz: http://arxiv.org/abs/2109.00960

Zobrazit plný text záznamu