Toward cross‐domain object detection in artwork images using improved YoloV5 and XGBoosting

Abstract

AbstractObject recognition in natural images has achieved great success, while recognizing objects in style‐images, such as artworks and watercolor images, has not yet achieved great progress. Here, this problem is addressed using cross‐domain object detection in style‐images, clipart, watercolor, and comic images. In particular, a cross‐domain object detection model is proposed using YoloV5 and eXtreme Gradient Boosting (XGBoosting). As detecting difficult instances in cross domain images is a challenging task, XGBoosting is incorporated in this workflow to enhance learning of the proposed model for application on hard‐to‐detect samples. Several ablation studies are carried out by training and evaluating this model on the StyleObject7K, ClipArt1K, Watercolor2K, and Comic2K datasets. It is empirically established that this proposed model works better than other methods for the above‐mentioned datasets.