RegNet: Self-Regulated Network for Image Classification

Jing Xu

doi:10.1109/TNNLS.2022.3158966

RegNet: Self-Regulated Network for Image Classification

2023-11-01

56

OA

AI

DOI：10.1109/TNNLS.2022.3158966

Original

Original request for help

Save

Abstract

En 中文

The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the information communication of intermediate layers of blocks is ignored. To address this issue, in this brief, we propose to introduce a regulator module as a memory mechanism to extract complementary features of the intermediate layers, which are further fed to the ResNet. In particular, the regulator module is composed of convolutional recurrent neural networks (RNNs) [e.g., convolutional long short-term memories (LSTMs) or convolutional gated recurrent units (GRUs)], which are shown to be good at extracting spatio-temporal information. We named the new regulated network as regulated residual network (RegNet). The regulator module can be easily implemented and appended to any ResNet architecture. Experimental results on three image classification datasets have demonstrated the promising performance of the proposed architecture compared with the standard ResNet, squeeze-and-excitation ResNet, and other state-of-the-art architectures.

Keywords:

Regulators

Correlation

Convolution

Task analysis

Feature extraction

Computer architecture

Residual neural networks

Convolutional neural networks (CNNs)

convolutional recurrent neural networks (RNNs)

residue networks

RegNet: Self-Regulated Network for Image Classification

Abstract

Journal

Organization