Zobrazeno 1 - 10
of 422
pro vyhledávání: '"P. Dubbelman"'
Cameras can be used to perceive the environment around the vehicle, while affordable radar sensors are popular in autonomous driving systems as they can withstand adverse weather conditions unlike cameras. However, radar point clouds are sparser with
Externí odkaz:
http://arxiv.org/abs/2411.13311
In this report, we present the first place solution to the ECCV 2024 BRAVO Challenge, where a model is trained on Cityscapes and its robustness is evaluated on several out-of-distribution datasets. Our solution leverages the powerful representations
Externí odkaz:
http://arxiv.org/abs/2409.17208
Autor:
Vu, Tuan-Hung, Valle, Eduardo, Bursuc, Andrei, Kerssies, Tommie, de Geus, Daan, Dubbelman, Gijs, Qian, Long, Zhu, Bingke, Chen, Yingying, Tang, Ming, Wang, Jinqiao, Vojíř, Tomáš, Šochman, Jan, Matas, Jiří, Smith, Michael, Ferrie, Frank, Basu, Shamik, Sakaridis, Christos, Van Gool, Luc
We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios. We define two categories of reliability: (1) semantic reliability, whic
Externí odkaz:
http://arxiv.org/abs/2409.15107
Autor:
de Geus, Daan, Dubbelman, Gijs
Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their parent objec
Externí odkaz:
http://arxiv.org/abs/2406.10114
This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges similar tokens w
Externí odkaz:
http://arxiv.org/abs/2406.09936
Achieving robust generalization across diverse data domains remains a significant challenge in computer vision. This challenge is important in safety-critical applications, where deep-neural-network-based systems must perform reliably under various e
Externí odkaz:
http://arxiv.org/abs/2406.09896
Recent vision foundation models (VFMs) have demonstrated proficiency in various tasks but require supervised fine-tuning to perform the task of semantic segmentation effectively. Benchmarking their performance is essential for selecting current model
Externí odkaz:
http://arxiv.org/abs/2404.12172
This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs). Existing works have proposed token reduction approac
Externí odkaz:
http://arxiv.org/abs/2306.02095
Autor:
Rosanne L. van den Berg, Casper de Boer, Marissa D. Zwan, Roos J. Jutten, Mariska van Liere, Marie-Christine A.B.J. van de Glind, Mark A. Dubbelman, Lisa Marie Schlüter, Argonde C. van Harten, Charlotte E. Teunissen, Elsmarieke van de Giessen, Frederik Barkhof, Lyduine E. Collij, Jessica Robin, William Simpson, John E Harrison, Wiesje M. van der Flier, Sietske A.M. Sikkes
Publikováno v:
Alzheimer’s Research & Therapy, Vol 16, Iss 1, Pp 1-14 (2024)
Abstract Background Digital speech assessment has potential relevance in the earliest, preclinical stages of Alzheimer’s disease (AD). We evaluated the feasibility, test-retest reliability, and association with AD-related amyloid-beta (Aβ) patholo
Externí odkaz:
https://doaj.org/article/75ea7ee6329e4654a1896779b7cc2a38
Autor:
de Geus, Daan, Dubbelman, Gijs
Unified panoptic segmentation methods are achieving state-of-the-art results on several datasets. To achieve these results on high-resolution datasets, these methods apply crop-based training. In this work, we find that, although crop-based training
Externí odkaz:
http://arxiv.org/abs/2304.08222