Dynamic Supervisor for Cross-dataset Object Detection

TL;DR

This paper introduces a dynamic supervisor framework for cross-dataset object detection that iteratively updates annotations using both hard and soft labels, significantly improving annotation quality and detection performance.

Contribution

It proposes a novel dynamic supervisor method that combines hard and soft label training to enhance annotation quality in cross-dataset object detection.

Findings

Both recall and precision of annotations are improved.

The dynamic supervisor outperforms existing methods across various dataset combinations.

Iterative annotation updates lead to superior detection accuracy.

Abstract

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem, recent studies focus on the generation of high-quality missing annotations. In this study, we first point out that it is not enough to generate high-quality annotations using a single model, which only looks once for annotations. Through detailed experimental analyses, we further conclude that hard-label training is conducive to generating high-recall annotations, while soft-label training tends to obtain high-precision annotations. Inspired by the aspects mentioned above, we propose a dynamic supervisor framework that updates the annotations multiple times through multiple-updated submodels trained using hard and soft labels. In the final generated annotations, both recall and precision improve significantly through the integration of hard-label training with soft-label training. Extensive experiments conducted on various dataset combination settings support our analyses and demonstrate the superior performance of the proposed dynamic supervisor.