High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Hongxing, Chen, Lide, Zhu, Hui, Chen, Yan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911256659623936
author Peng, Hongxing
Chen, Lide
Zhu, Hui
Chen, Yan
author_facet Peng, Hongxing
Chen, Lide
Zhu, Hui
Chen, Yan
contents Object detection in Unmanned Aerial Vehicle (UAV) imagery is fundamentally challenged by a prevalence of small, densely packed, and occluded objects within cluttered backgrounds. Conventional detectors struggle with this domain, as they rely on hand-crafted components like pre-defined anchors and heuristic-based Non-Maximum Suppression (NMS), creating a well-known performance bottleneck in dense scenes. Even recent end-to-end frameworks have not been purpose-built to overcome these specific aerial challenges, resulting in a persistent performance gap. To bridge this gap, we introduce HEDS-DETR, a holistically enhanced real-time Detection Transformer tailored for aerial scenes. Our framework features three key innovations. First, we propose a novel High-Frequency Enhanced Semantics Network (HFESNet) backbone, which yields highly discriminative features by preserving critical high-frequency details alongside robust semantic context. Second, our Efficient Small Object Pyramid (ESOP) counteracts information loss by efficiently fusing high-resolution features, significantly boosting small object detection. Finally, we enhance decoder stability and localization precision with two synergistic components: Selective Query Recollection (SQR) and Geometry-Aware Positional Encoding (GAPE), which stabilize optimization and provide explicit spatial priors for dense object arrangements. On the VisDrone dataset, HEDS-DETR achieves a +3.8% AP and +5.1% AP50 gain over its baseline while reducing parameters by 4M and maintaining real-time speeds. This demonstrates a highly competitive accuracy-efficiency balance, especially for detecting dense and small objects in aerial scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00825
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery
Peng, Hongxing
Chen, Lide
Zhu, Hui
Chen, Yan
Computer Vision and Pattern Recognition
I.2.10; I.4.8; I.5.1
Object detection in Unmanned Aerial Vehicle (UAV) imagery is fundamentally challenged by a prevalence of small, densely packed, and occluded objects within cluttered backgrounds. Conventional detectors struggle with this domain, as they rely on hand-crafted components like pre-defined anchors and heuristic-based Non-Maximum Suppression (NMS), creating a well-known performance bottleneck in dense scenes. Even recent end-to-end frameworks have not been purpose-built to overcome these specific aerial challenges, resulting in a persistent performance gap. To bridge this gap, we introduce HEDS-DETR, a holistically enhanced real-time Detection Transformer tailored for aerial scenes. Our framework features three key innovations. First, we propose a novel High-Frequency Enhanced Semantics Network (HFESNet) backbone, which yields highly discriminative features by preserving critical high-frequency details alongside robust semantic context. Second, our Efficient Small Object Pyramid (ESOP) counteracts information loss by efficiently fusing high-resolution features, significantly boosting small object detection. Finally, we enhance decoder stability and localization precision with two synergistic components: Selective Query Recollection (SQR) and Geometry-Aware Positional Encoding (GAPE), which stabilize optimization and provide explicit spatial priors for dense object arrangements. On the VisDrone dataset, HEDS-DETR achieves a +3.8% AP and +5.1% AP50 gain over its baseline while reducing parameters by 4M and maintaining real-time speeds. This demonstrates a highly competitive accuracy-efficiency balance, especially for detecting dense and small objects in aerial scenes.
title High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery
topic Computer Vision and Pattern Recognition
I.2.10; I.4.8; I.5.1
url https://arxiv.org/abs/2507.00825