Department of Computer Engineering, Hongik University, Mapo-gu, Seoul 04066, Republic of Korea.
Sensors (Basel). 2023 Feb 26;23(5):2589. doi: 10.3390/s23052589.
Although detecting small objects is critical in various applications, neural network models designed and trained for generic object detection struggle to do so with precision. For example, the popular Single Shot MultiBox Detector (SSD) tends to perform poorly for small objects, and balancing the performance of SSD across different sized objects remains challenging. In this study, we argue that the current IoU-based matching strategy used in SSD reduces the training efficiency for small objects due to improper matches between default boxes and ground truth objects. To address this issue and improve the performance of SSD in detecting small objects, we propose a new matching strategy called aligned matching that considers aspect ratios and center-point distance in addition to IoU. The results of experiments on the TT100K and Pascal VOC datasets show that SSD with aligned matching detected small objects significantly better without sacrificing performance on large objects or requiring extra parameters.
虽然在各种应用中检测小物体至关重要，但为通用物体检测设计和训练的神经网络模型在精确检测方面却存在困难。例如，流行的单阶段多框检测器（SSD）在检测小物体时往往表现不佳，并且平衡 SSD 在不同大小物体上的性能仍然具有挑战性。在本研究中，我们认为 SSD 中当前基于 IoU 的匹配策略由于默认框和真实对象之间的不恰当匹配，降低了小物体的训练效率。为了解决这个问题并提高 SSD 在检测小物体方面的性能，我们提出了一种新的匹配策略，称为对齐匹配，该策略除了 IoU 之外还考虑了纵横比和中心点距离。在 TT100K 和 Pascal VOC 数据集上的实验结果表明，带有对齐匹配的 SSD 在不牺牲大物体性能或不增加额外参数的情况下，显著提高了小物体的检测效果。
