all AI news
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions
March 26, 2024, 4:46 a.m. | Kaiwen Wang, Yinzhe Shen, Martin Lauer
cs.CV updates on arXiv.org arxiv.org
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
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote