Search papers, labs, and topics across Lattice.
UHR-DETR addresses the challenge of small object detection in ultra-high-resolution remote sensing imagery by efficiently managing computational resources. It introduces a Coverage-Maximizing Sparse Encoder to focus on informative high-resolution regions and a Global-Local Decoupled Decoder to resolve semantic ambiguities. Experiments on UHR datasets show a 2.8% mAP improvement and a 10x inference speedup compared to sliding-window baselines, all under strict hardware constraints.
Achieve a 10x speedup in detecting tiny objects in massive satellite images without sacrificing accuracy, even on a single GPU.
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.