Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

A novel residual block: replace Conv1× 1 with Conv3×3 and stack more convolutions [PeerJ]

Dawei ZHANG, Ph.D, Zhejiang Normal University, Jinhua, Department of Computer Science

Zhonglong ZHENG, Zhejiang Normal University, Jinhua

deep learning - Convolutional neural network block notation - Data Science Stack Exchange

3 Convolutional neural networks - Deep Learning for Vision Systems

Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

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

Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network, Journal of Fluid Mechanics

Dawei ZHANG, Ph.D, Zhejiang Normal University, Jinhua, Department of Computer Science

Sensors, Free Full-Text

Illustration of asymmetric convolution blocks. traditional 3 × 3 layer

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

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