Small Object Detection in Complex Backgrounds with Multi-Scale Attention and Global Relation Modeling

TL;DR

This paper introduces a novel multi-scale attention and global relation modeling framework specifically designed to improve small object detection in complex backgrounds, addressing issues like feature degradation and localization errors.

Contribution

The paper proposes a new framework with a Residual Haar Wavelet Downsampling, Global Relation Modeling, and Cross-Scale Hybrid Attention modules tailored for small object detection.

Findings

Outperforms state-of-the-art detectors on RGBT-Tiny benchmark.

Enhances feature preservation and semantic awareness for small objects.

Improves localization accuracy and robustness in complex environments.

Abstract

Small object detection under complex backgrounds remains a challenging task due to severe feature degradation, weak semantic representation, and inaccurate localization caused by downsampling operations and background interference. Existing detection frameworks are mainly designed for general objects and often fail to explicitly address the unique characteristics of small objects, such as limited structural cues and strong sensitivity to localization errors. In this paper, we propose a multi-level feature enhancement and global relation modeling framework tailored for small object detection. Specifically, a Residual Haar Wavelet Downsampling module is introduced to preserve fine-grained structural details by jointly exploiting spatial-domain convolutional features and frequency-domain representations. To enhance global semantic awareness and suppress background noise, a Global Relation Modeling module is employed to capture long-range dependencies at high-level feature stages. Furthermore, a Cross-Scale Hybrid Attention module is designed to establish sparse and aligned interactions across multi-scale features, enabling effective fusion of high-resolution details and high-level semantic information with reduced computational overhead. Finally, a Center-Assisted Loss is incorporated to stabilize training and improve localization accuracy for small objects. Extensive experiments conducted on the large-scale RGBT-Tiny benchmark demonstrate that the proposed method consistently outperforms existing state-of-the-art detectors under both IoU-based and scale-adaptive evaluation metrics. These results validate the effectiveness and robustness of the proposed framework for small object detection in complex environments.