Vision Eagle Attention: a new lens for advancing image classification

TL;DR

This paper introduces Vision Eagle Attention, a novel convolutional spatial attention mechanism that enhances feature extraction in image classification, leading to improved accuracy on benchmark datasets with a lightweight ResNet-18 model.

Contribution

The paper presents a new attention mechanism that combines convolutional local feature capture with selective emphasis, integrated into ResNet-18 for improved image classification performance.

Findings

Improved classification accuracy on FashionMNIST, Intel Image Classification, and OracleMNIST datasets.

Efficient attention mechanism that emphasizes discriminative image regions.

Potential extension to other vision tasks like detection and segmentation.

Abstract

In computer vision tasks, the ability to focus on relevant regions within an image is crucial for improving model performance, particularly when key features are small, subtle, or spatially dispersed. Convolutional neural networks (CNNs) typically treat all regions of an image equally, which can lead to inefficient feature extraction. To address this challenge, I have introduced Vision Eagle Attention, a novel attention mechanism that enhances visual feature extraction using convolutional spatial attention. The model applies convolution to capture local spatial features and generates an attention map that selectively emphasizes the most informative regions of the image. This attention mechanism enables the model to focus on discriminative features while suppressing irrelevant background information. I have integrated Vision Eagle Attention into a lightweight ResNet-18 architecture, demonstrating that this combination results in an efficient and powerful model. I have evaluated the performance of the proposed model on three widely used benchmark datasets: FashionMNIST, Intel Image Classification, and OracleMNIST, with a primary focus on image classification. Experimental results show that the proposed approach improves classification accuracy. Additionally, this method has the potential to be extended to other vision tasks, such as object detection, segmentation, and visual tracking, offering a computationally efficient solution for a wide range of vision-based applications. Code is available at: https://github.com/MahmudulHasan11085/Vision-Eagle-Attention.git