Výsledky vyhledávání - "Goossens, Bart"

Report

Robust width: A lightweight and certifiable adversarial defense

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable from natu

Externí odkaz: http://arxiv.org/abs/2405.15971

Zobrazit plný text záznamu

Report

BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments

Autor: Liu, Yuanzhi, Fu, Yujia, Qin, Minghui, Xu, Yufeng, Xu, Baoxin, Chen, Fengdong, Goossens, Bart, Sun, Poly Z. H., Yu, Hongwei, Liu, Chun, Chen, Long, Tao, Wei, Zhao, Hui

The rapid developments of mobile robotics and autonomous navigation over the years are largely empowered by public datasets for testing and upgrading, such as sensor odometry and SLAM tasks. Impressive demos and benchmark scores have arisen, which ma

Externí odkaz: http://arxiv.org/abs/2306.14137

Zobrazit plný text záznamu

Report

Resolution based Feature Distillation for Cross Resolution Person Re-Identification

Autor: Munir, Asad, Lyu, Chengjin, Goossens, Bart, Philips, Wilfried, Micheloni, Christian

Person re-identification (re-id) aims to retrieve images of same identities across different camera views. Resolution mismatch occurs due to varying distances between person of interest and cameras, this significantly degrades the performance of re-i

Externí odkaz: http://arxiv.org/abs/2109.07871

Zobrazit plný text záznamu

Report

Simultaneous Localization and Mapping Related Datasets: A Comprehensive Survey

Autor: Liu, Yuanzhi, Fu, Yujia, Chen, Fengdong, Goossens, Bart, Tao, Wei, Zhao, Hui

Due to the complicated procedure and costly hardware, Simultaneous Localization and Mapping (SLAM) has been heavily dependent on public datasets for drill and evaluation, leading to many impressive demos and good benchmark scores. However, with a hug

Externí odkaz: http://arxiv.org/abs/2102.04036

Zobrazit plný text záznamu

Report

Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability

Autor: Ozbulak, Utku, Peck, Jonathan, De Neve, Wesley, Goossens, Bart, Saeys, Yvan, Van Messem, Arnout

Regional adversarial attacks often rely on complicated methods for generating adversarial perturbations, making it hard to compare their efficacy against well-known attacks. In this study, we show that effective regional perturbations can be generate

Externí odkaz: http://arxiv.org/abs/2007.03198

Zobrazit plný text záznamu