Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection. The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one, significantly improving label assignment and providing sufficient supervision information for network training. Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin. Besides, observing prominent noisy labels in the Tiny Object Detection in Aerial Images (AI-TOD) dataset, we are motivated to meticulously relabel it and release AI-TOD-v2 and its corresponding benchmark. In AI-TOD-v2, the missing annotation and location error problems are considerably mitigated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points improvement over state-of-the-art competitors on AI-TOD-v2. Datasets, codes, and more visualizations are available at: https://chasel-tsui.github.io/AI-TOD-v2/.

航拍图像中的微小物体检测 (TOD) 具有挑战性，因为一个微小的物体只包含几个像素。由于缺乏判别特征的监督，最先进的物体检测器在微小物体上不能提供令人满意的结果。我们的主要观察结果是，交并比 (IoU) 度量及其扩展对微小对象的位置偏差非常敏感，当用于基于锚的检测器时，这会极大地降低标签分配的质量。为了解决这个问题，我们提出了一种新的评估指标，称为归一化 Wasserstein 距离 (NWD) 和一种新的基于 RanKing 的分配 (RKA) 策略，用于微小物体检测。提出的 NWD-RKA 策略可以很容易地嵌入到各种基于锚点的检测器中，以取代标准的基于 IoU 阈值的检测器，显着改善标签分配并为网络训练提供足够的监督信息。在四个数据集上进行测试，NWD-RKA 可以持续大幅提高微小物体检测性能。此外，在航空图像中的微小物体检测 (AI-TOD) 数据集中观察到突出的噪声标签，我们有动力对其进行细致的重新标记并发布 AI-TOD-v2 及其相应的基准。在 AI-TOD-v2 中，缺失注释和位置错误问题得到了显着缓解，促进了更可靠的训练和验证过程。将 NWD-RKA 嵌入到 DetectoRS 中，检测性能在 AI-TOD-v2 上比最先进的竞争对手提高了 4.3 AP 点。数据集、代码和更多可视化可在以下网址获得：https://chasel-tsui.g​​ithub.io/AI-TOD-v2/。