Progressive Domain Adaptation for Object Detection

TL;DR

This paper introduces a progressive domain adaptation approach for object detection that uses an intermediate domain to improve adaptation from source to target, leveraging adversarial learning and weighted loss for better performance.

Contribution

It proposes a novel progressive adaptation method with an intermediate domain to enhance object detection across different data distributions.

Findings

Outperforms state-of-the-art in target domain detection accuracy

Effectively bridges large domain gaps with intermediate domain translation

Improves training stability and results in domain adaptation

Abstract

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribution. Domain adaptation provides a solution by adapting existing labels to the target testing data. However, a large gap between domains could make adaptation a challenging task, which leads to unstable training processes and sub-optimal results. In this paper, we propose to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks. This intermediate domain is constructed by translating the source images to mimic the ones in the target domain. To tackle the domain-shift problem, we adopt adversarial learning to align distributions at the feature level. In addition, a weighted task loss is applied to deal with unbalanced image quality in the intermediate domain. Experimental results show that our method performs favorably against the state-of-the-art method in terms of the performance on the target domain.