Domain Adaptation for Object Detection via Style Consistency

TL;DR

This paper presents a two-step domain adaptation method for object detection that uses style transfer for pixel adaptation and robust pseudo labeling to improve detector performance across different visual styles.

Contribution

The paper introduces a novel two-step domain adaptation approach combining style transfer and pseudo labeling for improved object detection in new domains.

Findings

Significant performance improvement over state-of-the-art methods.

Effective reduction of domain gap through style transfer.

Robust pseudo labeling enhances detection accuracy.

Abstract

We propose a domain adaptation approach for object detection. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to changes in the high-level features. For the first step, we use a style transfer method for pixel-adaptation of source images to the target domain. We find that enforcing low distance in the high-level features of the object detector between the style transferred images and the source images improves the performance in the target domain. For the second step, we propose a robust pseudo labelling approach to reduce the noise in both positive and negative sampling. Experimental evaluation is performed using the detector SSD300 on PASCAL VOC extended with the dataset proposed in arxiv:1803.11365 where the target domain images are of different styles. Our approach significantly improves the state-of-the-art performance in this benchmark.