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

arXiv: https://arxiv.org/abs/2603.03788 · HTML: https://mlsanity.com/paper/2603.03788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [Dense Distinct Query for End-to-End Object Detection](https://mlsanity.com/paper/2303.12776/) (2023)
- [A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds](https://mlsanity.com/paper/2007.12831/) (2020)
- [Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing](https://mlsanity.com/paper/2403.01105/) (2024)
- [Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines](https://mlsanity.com/paper/2406.14482/) (2024)
- [ASCNet: Asymmetric Sampling Correction Network for Infrared Image Destriping](https://mlsanity.com/paper/2401.15578/) (2024)

## Abstract (arXiv)

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.