A Discriminative Channel Diversification Network for Image Classification

TL;DR

This paper introduces a lightweight channel diversification block that enhances global context and discriminative features in CNNs, improving image classification accuracy with minimal added complexity.

Contribution

The paper proposes a novel, easy-to-implement attention module that focuses on discriminative channels at the end of networks, reducing complexity compared to existing methods.

Findings

Improves baseline network accuracy by about 3% on average.

Effective in enhancing global context and discriminative features.

Compatible with various CNN architectures.

Abstract

Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks. However, the performance improvement comes with additional model complexity and computation cost. In this paper, we propose a light-weight and effective attention module, called channel diversification block, to enhance the global context by establishing the channel relationship at the global level. Unlike other channel attention mechanisms, the proposed module focuses on the most discriminative features by giving more attention to the spatially distinguishable channels while taking account of the channel activation. Different from other attention models that plugin the module in between several intermediate layers, the proposed module is embedded at the end of the backbone networks, making it easy to implement. Extensive experiments on CIFAR-10, SVHN, and Tiny-ImageNet datasets demonstrate that the proposed module improves the performance of the baseline networks by a margin of 3% on average.