Label Assignment Matters: A Gaussian Assignment Strategy for Tiny Object Detection

Feng Zhang, Shilin Zhou, Yingqian Wang, Xueying Wang, Yi Hou

Abstract: Recently, impressive improvements have been achieved in general object detection. However, tiny object detection remains a very challenging problem since tiny objects only occupy a few pixels. Consequently, the label assignment strategies used in general object detectors are not suitable for tiny object detection, because these algorithms tend to assign few or even no positive samples for tiny objects. In this article, we propose a simple yet effective Gaussian assignment (GA) strategy to solve this problem. Specifically, we first model the bounding boxes as 2-D Gaussian distributions and then encode training samples with a threshold. This strategy can assign more high-quality positive samples for tiny objects and adjust the weight of positive samples to balance the contribution from different-size objects. Extensive experiments on four tiny object detection datasets show that the proposed strategy significantly and consistently improves the performance of single-stage tiny object detectors. In particular, with our strategy, we bridge the performance gap between single-stage and state-of-the-art multistage detectors on the AI-TOD dataset (24.2% versus 24.8% in mAP) while maintaining the inference speed. The code is available at https://github.com/zf020114/GaussianAssignment .