Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation

Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

Sensors, Free Full-Text

Multi-scale attention-based lightweight network with dilated convolutions for infrared and visible image fusion

Frontiers Convolutional Neural Network-Based Human Movement Recognition Algorithm in Sports Analysis

Xiaowei HE, Zhejiang Normal University, Jinhua, Department of Computer

Zhonglong ZHENG, Zhejiang Normal University, Jinhua

A lightweight segmentation network for endoscopic surgical instruments based on edge refinement and efficient self-attention [PeerJ]

Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification

Frontiers Crop classification in high-resolution remote sensing images based on multi-scale feature fusion semantic segmentation model

Applied Sciences, Free Full-Text