Domain Adaptation for Object Detection via Style Consistency

Adrian Lopez Rodriguez (Imperial College London), Krystian Mikolajczyk (Imperial College London)

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 \cite{inoue2018cross}, where the target domain images are of different styles. Our approach significantly improves the state-of-the-art performance in this benchmark.

DOI
10.5244/C.33.204
https://dx.doi.org/10.5244/C.33.204

Files
Paper (PDF)
Supplementary material (PDF)

BibTeX