Zobrazeno 1 - 10
of 413
pro vyhledávání: '"Rigoll, Gerhard"'
Susceptibility to Image Resolution in Face Recognition and Training Strategies to Enhance Robustness
Publikováno v:
Leibniz Transactions on Embedded Systems, Vol 8, Iss 1, Pp 01:1-01:20 (2022)
Many face recognition approaches expect the input images to have similar image resolution. However, in real-world applications, the image resolution varies due to different image capture mechanisms or sources, affecting the performance of face recogn
Externí odkaz:
https://doaj.org/article/3130652f4f9f457ba2d2aebe55459519
Taking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection. Recent advancements in multi-view detection and 3D object recognition have si
Externí odkaz:
http://arxiv.org/abs/2403.12573
Autor:
Wolters, Philipp, Gilg, Johannes, Teepe, Torben, Herzog, Fabian, Laouichi, Anouar, Hofmann, Martin, Rigoll, Gerhard
Low-cost, vision-centric 3D perception systems for autonomous driving have made significant progress in recent years, narrowing the gap to expensive LiDAR-based methods. The primary challenge in becoming a fully reliable alternative lies in robust de
Externí odkaz:
http://arxiv.org/abs/2403.07746
Multi-view aggregation promises to overcome the occlusion and missed detection challenge in multi-object detection and tracking. Recent approaches in multi-view detection and 3D object detection made a huge performance leap by projecting all views to
Externí odkaz:
http://arxiv.org/abs/2310.13350
Object detectors are at the heart of many semi- and fully autonomous decision systems and are poised to become even more indispensable. They are, however, still lacking in accessibility and can sometimes produce unreliable predictions. Especially con
Externí odkaz:
http://arxiv.org/abs/2309.03110
Autor:
Knoche, Martin, Rigoll, Gerhard
Nowadays, face recognition systems surpass human performance on several datasets. However, there are still edge cases that the machine can't correctly classify. This paper investigates the effect of a combination of machine and human operators in the
Externí odkaz:
http://arxiv.org/abs/2304.08134
Recently, face recognition systems have demonstrated remarkable performances and thus gained a vital role in our daily life. They already surpass human face verification accountability in many scenarios. However, they lack explanations for their pred
Externí odkaz:
http://arxiv.org/abs/2211.13735
Autor:
Herzog, Fabian, Chen, Junpeng, Teepe, Torben, Gilg, Johannes, Hörmann, Stefan, Rigoll, Gerhard
Smart City applications such as intelligent traffic routing or accident prevention rely on computer vision methods for exact vehicle localization and tracking. Due to the scarcity of accurately labeled data, detecting and tracking vehicles in 3D from
Externí odkaz:
http://arxiv.org/abs/2208.14167
Image resolution, or in general, image quality, plays an essential role in the performance of today's face recognition systems. To address this problem, we propose a novel combination of the popular triplet loss to improve robustness against image re
Externí odkaz:
http://arxiv.org/abs/2207.06726
Autor:
Yan, Jun, Yin, Huilin, Deng, Xiaoyang, Zhao, Ziming, Ge, Wancheng, Zhang, Hao, Rigoll, Gerhard
Adversarial training methods are state-of-the-art (SOTA) empirical defense methods against adversarial examples. Many regularization methods have been proven to be effective with the combination of adversarial training. Nevertheless, such regularizat
Externí odkaz:
http://arxiv.org/abs/2206.03727