SDA-xNet: Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation

09/21/2022
by   Qingbei Guo, et al.
0

Existing multi-scale solutions lead to a risk of just increasing the receptive field sizes while neglecting small receptive fields. Thus, it is a challenging problem to effectively construct adaptive neural networks for recognizing various spatial-scale objects. To tackle this issue, we first introduce a new attention dimension, i.e., depth, in addition to existing attention dimensions such as channel, spatial, and branch, and present a novel selective depth attention network to symmetrically handle multi-scale objects in various vision tasks. Specifically, the blocks within each stage of a given neural network, i.e., ResNet, output hierarchical feature maps sharing the same resolution but with different receptive field sizes. Based on this structural property, we design a stage-wise building module, namely SDA, which includes a trunk branch and a SE-like attention branch. The block outputs of the trunk branch are fused to globally guide their depth attention allocation through the attention branch. According to the proposed attention mechanism, we can dynamically select different depth features, which contributes to adaptively adjusting the receptive field sizes for the variable-sized input objects. In this way, the cross-block information interaction leads to a long-range dependency along the depth direction. Compared with other multi-scale approaches, our SDA method combines multiple receptive fields from previous blocks into the stage output, thus offering a wider and richer range of effective receptive fields. Moreover, our method can be served as a pluggable module to other multi-scale networks as well as attention networks, coined as SDA-xNet. Their combination further extends the range of the effective receptive fields towards small receptive fields, enabling interpretable neural networks. Our source code is available at <https://github.com/QingbeiGuo/SDA-xNet.git>.

READ FULL TEXT

page 1

page 10

page 11

page 12

page 13

research
09/13/2020

Attention Cube Network for Image Restoration

Recently, deep convolutional neural network (CNN) have been widely used ...
research
03/15/2019

Selective Kernel Networks

In standard Convolutional Neural Networks (CNNs), the receptive fields o...
research
08/27/2023

MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

In recent years, Transformer networks are beginning to replace pure conv...
research
08/27/2022

LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal

This paper focuses on the limitations of current over-parameterized shad...
research
11/07/2019

Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae

Segmentation of objects with various sizes is relatively less explored i...
research
01/20/2020

BARNet: Bilinear Attention Network with Adaptive Receptive Field for Surgical Instrument Segmentation

Surgical instrument segmentation is extremely important for computer-ass...
research
05/25/2019

DIANet: Dense-and-Implicit Attention Network

Attention-based deep neural networks (DNNs) that emphasize the informati...

Please sign up or login with your details

Forgot password? Click here to reset