HazyDet：面向雾霾场景下无人机视角目标检测的深度线索开源基准
HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes
AI总结：
针对雾霾下无人机视角目标检测缺乏基准的问题，提出HazyDet基准（含383,000实例）及DeCoDet检测器，通过深度条件核、渐进域微调和尺度不变损失，在真实雾霾场景实现最先进性能，mAP提升1.5%。
摘要：
在恶劣大气条件（尤其是雾霾）下，从空中平台进行目标检测对于实现稳健的无人机自主性至关重要。然而，该领域在很大程度上仍未得到充分探索，主要受限于缺乏专门的基准。为弥补这一空白，我们提出了HazyDet，这是首个专为雾霾条件下无人机视角目标检测设计的大规模基准。HazyDet包含383,000个真实世界实例，这些实例源自自然雾霾捕获以及由清晰图像增强合成的雾化场景，为推进检测算法提供了一个具有挑战性和真实性的测试平台。为解决雾霾引起的严重视觉退化问题，我们提出了深度条件检测器（DeCoDet），这是一种新颖的架构，集成了深度条件核，可根据深度线索动态调制特征表示。DeCoDet的实际有效性和鲁棒性通过其训练策略进一步增强，该策略采用渐进式域微调（PDFT）来应对合成到真实的域偏移，以及尺度不变翻新损失（SIRLoss）以确保从可能含噪声的深度标注中进行弹性学习。在HazyDet上的全面实证验证证实了我们统一的DeCoDet框架的优越性，其在具有挑战性的真实世界雾霾测试场景中达到了最先进的性能，比最接近的竞争对手高出显著的+1.5% mAP。我们的数据集和工具包可在https://github.com/GrokCV/HazyDet获取。
英文摘要：
Object detection from aerial platforms under adverse atmospheric conditions, particularly haze, is paramount for robust drone autonomy. Yet, this domain remains largely underexplored, primarily hindered by the absence of specialized benchmarks. To bridge this gap, we present \textit{HazyDet}, the first, large-scale benchmark specifically designed for drone-view object detection in hazy conditions. Comprising 383,000 real-world instances derived from both naturally hazy captures and synthetically hazed scenes augmented from clear images, HazyDet provides a challenging and realistic testbed for advancing detection algorithms. To address the severe visual degradation induced by haze, we propose the Depth-Conditioned Detector (DeCoDet), a novel architecture that integrates a Depth-Conditioned Kernel to dynamically modulate feature representations based on depth cues. The practical efficacy and robustness of DeCoDet are further enhanced by its training with a Progressive Domain Fine-Tuning (PDFT) strategy to navigate synthetic-to-real domain shifts, and a Scale-Invariant Refurbishment Loss (SIRLoss) to ensure resilient learning from potentially noisy depth annotations. Comprehensive empirical validation on HazyDet substantiates the superiority of our unified DeCoDet framework, which achieves state-of-the-art performance, surpassing the closest competitor by a notable +1.5\% mAP on challenging real-world hazy test scenarios. Our dataset and toolkit are available at https://github.com/GrokCV/HazyDet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
