PKCAM: Previous Knowledge Channel Attention Module

TL;DR

PKCAM introduces a lightweight attention module that captures cross-layer channel relations to enhance CNN performance in image classification and object detection tasks.

Contribution

The paper proposes PKCAM, a novel attention module that models global channel relations across layers, improving CNN accuracy with minimal computational overhead.

Findings

Consistent performance improvements on classification tasks.

Enhanced object detection accuracy.

Lightweight design suitable for various CNN architectures.

Abstract

Recently, attention mechanisms have been explored with ConvNets, both across the spatial and channel dimensions. However, from our knowledge, all the existing methods devote the attention modules to capture local interactions from a uni-scale. In this paper, we propose a Previous Knowledge Channel Attention Module(PKCAM), that captures channel-wise relations across different layers to model the global context. Our proposed module PKCAM is easily integrated into any feed-forward CNN architectures and trained in an end-to-end fashion with a negligible footprint due to its lightweight property. We validate our novel architecture through extensive experiments on image classification and object detection tasks with different backbones. Our experiments show consistent improvements in performances against their counterparts. Our code is published at https://github.com/eslambakr/EMCA.