Convolutional neural networks (CNNs) and vision transformers (ViT) have
...
This paper proposes a learnable nonlinear activation mechanism specifica...
Designing light-weight CNN models with little parameters and Flops is a
...
Traditionally, different types of feature operators (e.g., convolution,
...
Gradient descent algorithm is the most utilized method when optimizing
m...
Traditionally, CNN models possess hierarchical structures and utilize th...
Regularization plays a vital role in machine learning optimization. One ...
This paper proposes a novel nonlinear activation mechanism typically for...