Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integration

TL;DR

This paper introduces Local-Global Attention, a novel mechanism that adaptively integrates local and global features for improved multi-scale object detection and classification, outperforming existing methods in accuracy and efficiency.

Contribution

The paper presents a new attention mechanism combining multi-scale convolutions and learnable parameters to dynamically balance local and global features for better multi-scale detection.

Findings

Significantly improves object detection across multiple scales.

Outperforms existing attention methods in accuracy and efficiency.

Enhances detection of small and multi-class objects.

Abstract

In recent years, attention mechanisms have significantly enhanced the performance of object detection by focusing on key feature information. However, prevalent methods still encounter difficulties in effectively balancing local and global features. This imbalance hampers their ability to capture both fine-grained details and broader contextual information-two critical elements for achieving accurate object detection.To address these challenges, we propose a novel attention mechanism, termed Local-Global Attention, which is designed to better integrate both local and global contextual features. Specifically, our approach combines multi-scale convolutions with positional encoding, enabling the model to focus on local details while concurrently considering the broader global context. Additionally, we introduce a learnable parameters, which allow the model to dynamically adjust the relative importance of local and global attention, depending on the specific requirements of the task, thereby optimizing feature representations across multiple scales.We have thoroughly evaluated the Local-Global Attention mechanism on several widely used object detection and classification datasets. Our experimental results demonstrate that this approach significantly enhances the detection of objects at various scales, with particularly strong performance on multi-class and small object detection tasks. In comparison to existing attention mechanisms, Local-Global Attention consistently outperforms them across several key metrics, all while maintaining computational efficiency.