@inproceedings{ae957ff6c370412389f3173578020b2f,
title = "Enhancing Resilience: Redundancy Reduction for Object Detection in Adversarial Conditions",
abstract = "Vision systems, like other deep learning-based systems, encounter limitations due to training data and struggle to handle adversarial conditions such as varying lighting and weather conditions. In this paper, we propose a knowledge distillation framework aimed at bolstering the resilience of computer vision systems under adversarial conditions. Specifically, we focus on object detection task in adverse weather conditions and demonstrate that our system either exceeds or matches the state-of-the-art accuracy levels. Our system achieves a 2\% higher mean average precision (mAP@50) in hazy conditions, and 9\% higher mean average precision (mAP@50) in low-light conditions, compared to the nearest state-of-the-art frameworks.",
keywords = "adverse conditions, computer vision, knowledge distillation, object detection, redundancy reduction",
author = "Shubham Agarwal and Raz Birman and Ofer Hadar",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024 ; Conference date: 22-07-2024 Through 23-07-2024",
year = "2024",
month = jan,
day = "1",
doi = "10.1109/SPACE63117.2024.10668393",
language = "English",
series = "2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "580--583",
booktitle = "2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024",
address = "United States",
}