English

HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection

Computer Vision and Pattern Recognition 2022-07-26 v1

Abstract

Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do not explicitly establish the relationships between sample assignment and object detection performance. In this work, we propose a novel dynamic sample assignment scheme based on hyper-parameter search. We first define the number of positive samples assigned to each ground truth as the hyper-parameters and employ a surrogate optimization algorithm to derive the optimal choices. Then, we design a dynamic sample assignment procedure to dynamically select the optimal number of positives at each training iteration. Experiments demonstrate that the resulting HPS-Det brings improved performance over different object detection baselines. Moreover, We analyze the hyper-parameter reusability when transferring between different datasets and between different backbones for object detection, which exhibits the superiority and versatility of our method.

Keywords

Cite

@article{arxiv.2207.11539,
  title  = {HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection},
  author = {Ji Liu and Dong Li and Zekun Li and Han Liu and Wenjing Ke and Lu Tian and Yi Shan},
  journal= {arXiv preprint arXiv:2207.11539},
  year   = {2022}
}
R2 v1 2026-06-25T01:10:17.234Z