Domain Adaptation for Object Detection via Style Consistency
This work addresses the problem of object detection performance degradation across domains for computer vision applications, representing an incremental advance in domain adaptation techniques.
The paper tackles domain adaptation for object detection by using style transfer for pixel-level adaptation and a robust pseudo-labeling method for classifier adaptation, achieving significant state-of-the-art improvements on a benchmark with different style images.
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.