Stable Diffusion For Aerial Object Detection

Aerial object detection is a challenging task, in which one major obstacle lies in the limitations of large-scale data collection and the long-tail distribution of certain classes. Synthetic data offers a promising solution, especially with recent advances in diffusion-based methods like stable diffusion (SD). However, the direct application of diffusion methods to aerial domains poses unique challenges: stable diffusion's optimization for rich ground-level semantics doesn't align with the sparse nature of aerial objects, and the extraction of post-synthesis object coordinates remains problematic. To address these challenges, we introduce a synthetic data augmentation framework tailored for aerial images. It encompasses sparse-to-dense region of interest (ROI) extraction to bridge the semantic gap, fine-tuning the diffusion model with low-rank adaptation (LORA) to circumvent exhaustive retraining, and finally, a Copy-Paste method to compose synthesized objects with backgrounds, providing a nuanced approach to aerial object detection through synthetic data.

航空目标检测是一项极具挑战性的任务，其主要难点之一在于大规模数据采集的局限性，以及部分类别存在的长尾分布问题。合成数据为解决该类问题提供了颇具前景的方案，尤其是在以稳定扩散（Stable Diffusion, SD）为代表的扩散类模型近期取得显著进展的背景下。然而，将扩散方法直接应用于航空领域会面临独特挑战：稳定扩散针对丰富的地面层级语义所做的优化，与航空目标的稀疏分布特性并不匹配，且合成后目标坐标的提取仍存在难点。为解决上述挑战，我们提出了一种专为航空图像设计的合成数据增强框架。该框架涵盖三大核心环节：一是稀疏至稠密的感兴趣区域（Region of Interest, ROI）提取，以弥合语义鸿沟；二是采用低秩适配（Low-Rank Adaptation, LORA）对扩散模型进行微调，规避全量重训练的繁重开销；三是基于Copy-Paste方法将合成目标与背景图像进行融合，最终通过合成数据为航空目标检测提供更为精细化的解决方案。