Asymmetric Object–Background Latent Pretraining for Domain Adaptation

Author : Arthur Toder

Abstract : This article addresses the question of the consistency of unmanned aerial vehicle (UAV) detection under a strong change of environment. It presents a self-supervised pretraining strategy, applied to a state-of-the-art one-stage object detector, that decouples the learning of the objects of interest from the learning of the background. This greatly improves the detection of UAVs on urban backgrounds while requiring only rural UAV datasets.

Keywords : Computer vision, domain adaptation, object detection.

Conference Name : International Conference on Computational Vision and Robotics (ICCVR - 26)

Conference Place : Salzburg, Austria

Conference Date : 3rd Sep 2026