论文标题
一个比较的注意框架，可在空中图像上更好地射击对象检测
A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images
论文作者
论文摘要
在Pascal VOC和MS Coco等自然图像数据集上，很少有射击对象检测（FSOD）方法是在自然图像数据集上设计和评估的。但是，尚不清楚自然图像的最佳方法是否也是航空图像的最佳方法。此外，由于多种检测框架和培训策略，很难直接比较FSOD方法之间的性能。因此，我们提出了一个基准测试框架，该框架为实施和比较基于注意力的FSOD方法提供了灵活的环境。所提出的框架着重于注意机制，并分为三个模块：空间对齐，全球注意力和融合层。为了保持现有方法的竞争，这些方法通常利用复杂的培训，我们提出了为对象检测设计的新增强技术。使用此框架，重新进化并比较了几种FSOD方法。这种比较强调了关于空中和自然图像的两个不同的性能方案：FSOD在航空图像上的性能较差。我们的实验表明，在几个射击设置中很难检测到的小物体说明了性能差。最后，我们为FSOD开发了一种新型的多尺度一致性方法，即跨刻度查询支持对齐（XQSA），以改善对小物体的检测。 XQSA在Dota和Dior上的表现明显优于最先进的。
Few-Shot Object Detection (FSOD) methods are mainly designed and evaluated on natural image datasets such as Pascal VOC and MS COCO. However, it is not clear whether the best methods for natural images are also the best for aerial images. Furthermore, direct comparison of performance between FSOD methods is difficult due to the wide variety of detection frameworks and training strategies. Therefore, we propose a benchmarking framework that provides a flexible environment to implement and compare attention-based FSOD methods. The proposed framework focuses on attention mechanisms and is divided into three modules: spatial alignment, global attention, and fusion layer. To remain competitive with existing methods, which often leverage complex training, we propose new augmentation techniques designed for object detection. Using this framework, several FSOD methods are reimplemented and compared. This comparison highlights two distinct performance regimes on aerial and natural images: FSOD performs worse on aerial images. Our experiments suggest that small objects, which are harder to detect in the few-shot setting, account for the poor performance. Finally, we develop a novel multiscale alignment method, Cross-Scales Query-Support Alignment (XQSA) for FSOD, to improve the detection of small objects. XQSA outperforms the state-of-the-art significantly on DOTA and DIOR.
