Zobrazeno 1 - 10
of 1 149
pro vyhledávání: '"Paulitsch P."'
Autor:
Sha, Qutub Syed, Paulitsch, Michael, Pattabiraman, Karthik, Hagn, Korbinian, Oboril, Fabian, Buerkle, Cornelius, Scholl, Kay-Ulrich, Hinz, Gereon, Knoll, Alois
As transformer-based object detection models progress, their impact in critical sectors like autonomous vehicles and aviation is expected to grow. Soft errors causing bit flips during inference have significantly impacted DNN performance, altering pr
Externí odkaz:
http://arxiv.org/abs/2406.03229
Autor:
Syed, Qutub, Paulitsch, Michael, Hagn, Korbinian, Cihangir, Neslihan Kose, Scholl, Kay-Ulrich, Oboril, Fabian, Hinz, Gereon, Knoll, Alois
We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as autonomous driving. The Situa
Externí odkaz:
http://arxiv.org/abs/2406.03188
Autor:
Cai, Zhipeng, Mueller, Matthias, Birkl, Reiner, Wofk, Diana, Tseng, Shao-Yen, Cheng, JunDa, Stan, Gabriela Ben-Melech, Lal, Vasudev, Paulitsch, Michael
In the current era of generative AI breakthroughs, generating panoramic scenes from a single input image remains a key challenge. Most existing methods use diffusion-based iterative or simultaneous multi-view inpainting. However, the lack of global s
Externí odkaz:
http://arxiv.org/abs/2406.01843
Autor:
Chen, Yujin, Nie, Yinyu, Ummenhofer, Benjamin, Birkl, Reiner, Paulitsch, Michael, Müller, Matthias, Nießner, Matthias
We present Mesh2NeRF, an approach to derive ground-truth radiance fields from textured meshes for 3D generation tasks. Many 3D generative approaches represent 3D scenes as radiance fields for training. Their ground-truth radiance fields are usually f
Externí odkaz:
http://arxiv.org/abs/2403.19319
Autor:
Yuan, Kai, Bauinger, Christoph, Zhang, Xiangyi, Baehr, Pascal, Kirchhart, Matthias, Dabert, Darius, Tousnakhoff, Adrien, Boudier, Pierre, Paulitsch, Michael
This paper presents a SYCL implementation of Multi-Layer Perceptrons (MLPs), which targets and is optimized for the Intel Data Center GPU Max 1550. To increase the performance, our implementation minimizes the slow global memory accesses by maximizin
Externí odkaz:
http://arxiv.org/abs/2403.17607
Autor:
Stan, Gabriela Ben Melech, Wofk, Diana, Aflalo, Estelle, Tseng, Shao-Yen, Cai, Zhipeng, Paulitsch, Michael, Lal, Vasudev
Latent diffusion models have proven to be state-of-the-art in the creation and manipulation of visual outputs. However, as far as we know, the generation of depth maps jointly with RGB is still limited. We introduce LDM3D-VR, a suite of diffusion mod
Externí odkaz:
http://arxiv.org/abs/2311.03226
Publikováno v:
In: Guiochet, J., Tonetta, S., Bitsch, F. (eds) Computer Safety, Reliability, and Security. SAFECOMP 2023. Lecture Notes in Computer Science, vol 14181. Springer, Cham
We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet can efficiently detect silent data corruption originating from both ha
Externí odkaz:
http://arxiv.org/abs/2310.20349
Transient or permanent faults in hardware can render the output of Neural Networks (NN) incorrect without user-specific traces of the error, i.e. silent data errors (SDE). On the other hand, modern NNs also possess an inherent redundancy that can tol
Externí odkaz:
http://arxiv.org/abs/2310.19449
Autor:
Qutub, Syed Sha, Kose, Neslihan, Rosales, Rafael, Paulitsch, Michael, Hagn, Korbinian, Geissler, Florian, Peng, Yang, Hinz, Gereon, Knoll, Alois
This paper introduces the Budding Ensemble Architecture (BEA), a novel reduced ensemble architecture for anchor-based object detection models. Object detection models are crucial in vision-based tasks, particularly in autonomous systems. They should
Externí odkaz:
http://arxiv.org/abs/2309.08036
Autor:
Abella, Jaume, Cazorla, Francisco J., Alcaide, Sergi, Paulitsch, Michael, Peng, Yang, Gouveia, Inês Pinto
HPC (High Performance Computing) devices increasingly become the only alternative to deliver the performance needed in safety-critical autonomous systems (e.g., autonomous cars, unmanned planes) due to deploying large and powerful multicores along wi
Externí odkaz:
http://arxiv.org/abs/2307.11940