融合应对多样条件：面向无人机多模态目标检测的高多样性基准与条件提示基线
Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues
AI总结：
针对无人机多模态检测数据集条件多样性不足的问题，提出高多样性基准ATR-UMOD及条件感知动态融合方法PCDF，利用条件提示自适应融合RGB与红外信息，实验验证其有效性。
摘要：
基于无人机（UAV）的可见光（RGB）与红外（IR）图像目标检测，在深度学习技术进展与高质量数据集可获取性的推动下，实现了稳健的全天候检测能力。然而，现有数据集因成像条件有限，难以充分捕捉真实世界的复杂性。为此，我们引入一个高多样性数据集ATR-UMOD，涵盖不同场景，飞行高度从80米到300米，角度从0°到75°，并在丰富的天气与光照条件下覆盖全天候、全年份的时间变化。此外，每个RGB-IR图像对标注了6个条件属性，提供了有价值的高层上下文信息。为应对此类多样条件带来的挑战，我们提出一种新颖的提示引导的条件感知动态融合（PCDF）方法，通过利用标注的条件提示，自适应地重新分配多模态贡献。通过将成像条件编码为文本提示，PCDF通过任务特定的软门控变换有效建模条件与多模态贡献之间的关系。一个提示引导的条件解耦模块进一步确保了在无条件标注的实际应用中的可用性。在ATR-UMOD数据集上的实验验证了PCDF的有效性。
英文摘要：
Unmanned aerial vehicles (UAV)-based object detection with visible (RGB) and infrared (IR) images facilitates robust around-the-clock detection, driven by advancements in deep learning techniques and the availability of high-quality dataset. However, the existing dataset struggles to fully capture real-world complexity for limited imaging conditions. To this end, we introduce a high-diversity dataset ATR-UMOD covering varying scenarios, spanning altitudes from 80m to 300m, angles from 0° to 75°, and all-day, all-year time variations in rich weather and illumination conditions. Moreover, each RGB-IR image pair is annotated with 6 condition attributes, offering valuable high-level contextual information. To meet the challenge raised by such diverse conditions, we propose a novel prompt-guided condition-aware dynamic fusion (PCDF) to adaptively reassign multimodal contributions by leveraging annotated condition cues. By encoding imaging conditions as text prompts, PCDF effectively models the relationship between conditions and multimodal contributions through a task-specific soft-gating transformation. A prompt-guided condition-decoupling module further ensures the availability in practice without condition annotations. Experiments on ATR-UMOD dataset reveal the effectiveness of PCDF.
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。
