Search Results for author: Chengyang Liang

Found 2 papers, 0 papers with code

Domain Adaptive Object Detection via Feature Separation and Alignment

no code implementations16 Dec 2020 Chengyang Liang, Zixiang Zhao, Junmin Liu, Jiangshe Zhang

Notably, scale-space filtering is exploited to implement adaptive searching for regions to be aligned, and instance-level features in each region are refined to reduce redundancy and noise mentioned in the second issue.

object-detection Object Detection

Efficient and Model-Based Infrared and Visible Image Fusion Via Algorithm Unrolling

no code implementations12 May 2020 Zixiang Zhao, Shuang Xu, Jiangshe Zhang, Chengyang Liang, Chunxia Zhang, Junmin Liu

The proposed AUIF model starts with the iterative formulas of two traditional optimization models, which are established to accomplish two-scale decomposition, i. e., separating low-frequency base information and high-frequency detail information from source images.

Decoder Infrared And Visible Image Fusion +1

Cannot find the paper you are looking for? You can Submit a new open access paper.