UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects

2026-02-26

AI Summary

This work proposes UFO-DETR, an end-to-end detection framework designed to address the challenges of tiny object detection in drone imagery, including large scale variations, dense distributions, and the limited performance of general-purpose detectors. UFO-DETR integrates the LSKNet backbone with DAttention and AIFI modules to effectively model multi-scale spatial relationships. It further introduces the novel DynFreq-C3 module, which enhances small object representation through cross-spatial-frequency feature augmentation. While maintaining a lightweight and efficient architecture, UFO-DETR significantly outperforms RT-DETR-L in both accuracy and computational efficiency, making it well-suited for edge computing scenarios in unmanned aerial vehicle applications.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Small target detection in UAV imagery faces significant challenges such as scale variations, dense distribution, and the dominance of small targets. Existing algorithms rely on manually designed components, and general-purpose detectors are not optimized for UAV images, making it difficult to balance accuracy and complexity. To address these challenges, this paper proposes an end-to-end object detection framework, UFO-DETR, which integrates an LSKNet-based backbone network to optimize the receptive field and reduce the number of parameters. By combining the DAttention and AIFI modules, the model flexibly models multi-scale spatial relationships, improving multi-scale target detection performance. Additionally, the DynFreq-C3 module is proposed to enhance small target detection capability through cross-space frequency feature enhancement. Experimental results show that, compared to RT-DETR-L, the proposed method offers significant advantages in both detection performance and computational efficiency, providing an efficient solution for UAV edge computing.

Problem

• UAV
• small object detection
• scale variation
• dense distribution
• edge computing

Innovation

• UFO-DETR
• frequency feature enhancement
• end-to-end detection
• small object detection
• UAV imagery