DA^2-Net : Diverse Adaptive Attention Convolutional Neural Network

11/25/2021
by   Abenezer Girma, et al.
0

Standard Convolutional Neural Network (CNN) designs rarely focus on the importance of explicitly capturing diverse features to enhance the network's performance. Instead, most existing methods follow an indirect approach of increasing or tuning the networks' depth and width, which in many cases significantly increases the computational cost. Inspired by a biological visual system, we propose a Diverse and Adaptive Attention Convolutional Network (DA^2-Net), which enables any feed-forward CNNs to explicitly capture diverse features and adaptively select and emphasize the most informative features to efficiently boost the network's performance. DA^2-Net incurs negligible computational overhead and it is designed to be easily integrated with any CNN architecture. We extensively evaluated DA^2-Net on benchmark datasets, including CIFAR100, SVHN, and ImageNet, with various CNN architectures. The experimental results show DA^2-Net provides a significant performance improvement with very minimal computational overhead.

READ FULL TEXT
research
09/05/2022

LKD-Net: Large Kernel Convolution Network for Single Image Dehazing

The deep convolutional neural networks (CNNs)-based single image dehazin...
research
04/11/2018

Attention U-Net: Learning Where to Look for the Pancreas

We propose a novel attention gate (AG) model for medical imaging that au...
research
03/29/2021

FocusedDropout for Convolutional Neural Network

In convolutional neural network (CNN), dropout cannot work well because ...
research
02/14/2022

Convolutional Neural Network with Convolutional Block Attention Module for Finger Vein Recognition

Convolutional neural networks have become a popular research in the fiel...
research
01/12/2023

DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention

Single image dehazing is a challenging ill-posed problem which estimates...
research
06/21/2017

GM-Net: Learning Features with More Efficiency

Deep Convolutional Neural Networks (CNNs) are capable of learning unprec...
research
10/18/2018

S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction

Recent studies have used deep residual convolutional neural networks (CN...

Please sign up or login with your details

Forgot password? Click here to reset