Tiny object detection is becoming one of the most challenging tasks in computer vision because of the limited object size and lack of information. The label assignment strategy is a key factor affecting the accuracy of object detection. Although there are some effective label assignment strategies for tiny objects, most of them focus on reducing the sensitivity to the bounding boxes to increase the number of positive samples and have some fixed hyperparameters need to set. However, more positive samples may not necessarily lead to better detection results, in fact, excessive positive samples may lead to more false positives. In this paper, we introduce a simple but effective strategy named the Similarity Distance (SimD) to evaluate the similarity between bounding boxes. This proposed strategy not only considers both location and shape similarity but also learns hyperparameters adaptively, ensuring that it can adapt to different datasets and various object sizes in a dataset. Our approach can be simply applied in common anchor-based detectors in place of the IoU for label assignment and Non Maximum Suppression (NMS). Extensive experiments on four mainstream tiny object detection datasets demonstrate superior performance of our method, especially, 1.8 AP points and 4.1 AP points of very tiny higher than the state-of-the-art competitors on AI-TOD. Code is available at: \url{https://github.com/cszzshi/SimD}.

翻译：小目标检测因目标尺寸有限且信息匮乏，正逐渐成为计算机视觉领域最具挑战性的任务之一。标签分配策略是影响目标检测精度的关键因素。尽管目前已存在一些针对小目标的有效标签分配策略，但大多侧重于降低对边界框的敏感性以增加正样本数量，且需要设置一些固定的超参数。然而，更多正样本未必能带来更好的检测结果，实际上，过多的正样本可能导致误检率上升。本文提出一种简单而有效的策略，称为相似性距离（SimD），用于评估边界框之间的相似度。该策略不仅同时考虑了位置相似性与形状相似性，还能自适应地学习超参数，确保其能适应不同数据集及同一数据集中不同尺寸的目标。我们的方法可简便地应用于常见的基于锚框的检测器中，以替代交并比（IoU）进行标签分配和非极大值抑制（NMS）。在四个主流小目标检测数据集上的大量实验表明，本方法具有优越的性能，尤其在AI-TOD数据集上，对极小目标的检测精度分别比现有最优方法高出1.8和4.1个AP点。代码发布于：\url{https://github.com/cszzshi/SimD}。