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

TL;DR

HPS-Det introduces a hyper-parameter search-based dynamic sample assignment method that optimizes positive sample selection during training, leading to improved object detection performance across various baselines, datasets, and backbones.

Contribution

The paper presents a novel hyper-parameter search approach for dynamic sample assignment in object detection, explicitly linking assignment to detection performance.

Findings

Improved detection accuracy across multiple baselines.

Effective hyper-parameter reusability across datasets.

Versatility with different backbones.

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.