Zhi-Xuan Chen — accepted AI-conference papers

2023

LGPConv: Learnable Gaussian Perturbation Convolution for Lightweight Pansharpening

Chen-Yu Zhao, Tian-Jing Zhang, Ran Ran, Zhi-Xuan Chen, Liang-Jian Deng

IJCAI 2023poster

Pansharpening is a crucial and challenging task that aims to obtain a high spatial resolution image by merging a multispectral (MS) image and a panchromatic (PAN) image. Current methods use CNNs with standard convolution, but we've observed strong correlation among channel dimensions in the kernel,…

Cited by 9 Source ↗PDF ↗Scholar ↗

2022

SpanConv: A New Convolution via Spanning Kernel Space for Lightweight Pansharpening

Zhi-Xuan Chen, Cheng Jin, Tian-Jing Zhang, Xiao Wu, Liang-Jian Deng

IJCAI 2022poster

Standard convolution operations can effectively perform feature extraction and representation but result in high computational cost, largely due to the generation of the original convolution kernel corresponding to the channel dimension of the feature map, which will cause unnecessary redundancy. In…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗