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

2026-03-04

AI Summary

This work addresses the challenges of small object detection in complex backgrounds, where performance is hindered by feature degradation, weak semantic cues, and inaccurate localization. To overcome these limitations, we propose a multi-level feature enhancement framework with global relation modeling. Specifically, residual Haar wavelet downsampling is employed to preserve structural details, while a global relation module suppresses background interference. A cross-scale hybrid attention mechanism enables efficient multi-scale feature fusion, and a center-assisted loss function is introduced to refine localization accuracy. Evaluated on the RGBT-Tiny benchmark, the proposed method significantly outperforms existing state-of-the-art approaches, achieving superior performance in both IoU-based metrics and scale-adaptive evaluation criteria.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

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.

Problem

• Small Object Detection
• Complex Backgrounds
• Feature Degradation
• Localization Accuracy
• Semantic Representation

Innovation

• Multi-Scale Attention
• Global Relation Modeling
• Haar Wavelet Downsampling
• Small Object Detection
• Cross-Scale Hybrid Attention