UHR-DETR: Efficient End-to-End Small Object Detection for Ultra-High-Resolution Remote Sensing Imagery

2026-04-23

AI Summary

This work addresses the challenges of small object detection in ultra-high-resolution remote sensing imagery, where direct processing of full-resolution images is constrained by GPU memory limitations, while downsampling or cropping often leads to target omission or contextual fragmentation. To overcome these issues, the authors propose an end-to-end Transformer-based detector featuring a coverage-maximized sparse encoder and a global–local decoupled decoder. This architecture dynamically focuses on high-information regions and integrates multi-scale features, achieving a balance among computational efficiency, object coverage, and semantic consistency under strict memory constraints. Evaluated on the STAR dataset, the method improves mean average precision (mAP) by 2.8% over a sliding-window baseline, accelerates inference by 10×, and operates efficiently on a single GPU with 24 GB of memory.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Hardware-aware ML
• Search and Optimization: Distributed Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Ultra-High-Resolution (UHR) imagery has become essential for modern remote sensing, offering unprecedented spatial coverage. However, detecting small objects in such vast scenes presents a critical dilemma: retaining the original resolution for small objects causes prohibitive memory bottlenecks. Conversely, conventional compromises like image downsampling or patch cropping either erase small objects or destroy context. To break this dilemma, we propose UHR-DETR, an efficient end-to-end transformer-based detector designed for UHR imagery. First, we introduce a Coverage-Maximizing Sparse Encoder that dynamically allocates finite computational resources to informative high-resolution regions, ensuring maximum object coverage with minimal spatial redundancy. Second, we design a Global-Local Decoupled Decoder. By integrating macroscopic scene awareness with microscopic object details, this module resolves semantic ambiguities and prevents scene fragmentation. Extensive experiments on the UHR imagery datasets (e.g., STAR and SODA-A) demonstrate the superiority of UHR-DETR under strict hardware constraints (e.g., a single 24GB RTX 3090). It achieves a 2.8\% mAP improvement while delivering a 10$\times$ inference speedup compared to standard sliding-window baselines on the STAR dataset. Our codes and models will be available at https://github.com/Li-JingFang/UHR-DETR.

Problem

• Ultra-High-Resolution
• Small Object Detection
• Remote Sensing Imagery
• Memory Bottleneck
• Context Preservation

Innovation

• UHR-DETR
• small object detection
• sparse encoder
• global-local decoupled decoder
• ultra-high-resolution remote sensing