Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions

arXiv:2403.15786v1 Announce Type: new
Abstract: Existing object detectors encounter challenges in handling domain shifts between training and real-world data, particularly under poor visibility conditions like fog and night. Cutting-edge cross-domain object detection methods use teacher-student frameworks and compel teacher and student models to produce consistent predictions under weak and strong augmentations, respectively. In this paper, we reveal that manually crafted augmentations are insufficient for optimal teaching and present a simple yet effective framework named Adversarial Defense Teacher (ADT), leveraging adversarial …

abstract adversarial arxiv challenges consistent cs.cv data defense detection detection methods domain edge frameworks object predictions training type visibility world