Picture for Mathieu Salzmann

Mathieu Salzmann

Attention-based Domain Adaptation for Single Stage Detectors

Jun 14, 2021
Vidit, Mathieu Salzmann

Figure 1 for Attention-based Domain Adaptation for Single Stage Detectors

Figure 2 for Attention-based Domain Adaptation for Single Stage Detectors

Figure 3 for Attention-based Domain Adaptation for Single Stage Detectors

Figure 4 for Attention-based Domain Adaptation for Single Stage Detectors

Access Paper or Ask Questions

DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

May 30, 2021
Samuel von Baußnern, Johannes Otterbach, Adrian Loy, Mathieu Salzmann, Thomas Wollmann

Figure 1 for DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

Figure 2 for DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

Figure 3 for DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

Figure 4 for DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows

* 14 pages, 4 figures, 4 tables

Access Paper or Ask Questions

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

Apr 30, 2021
Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Mathieu Salzmann, Pascal Fua, Matthias Rottmann

Figure 1 for SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

Figure 2 for SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

Figure 3 for SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

Figure 4 for SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

* 10 pages, 13 figures, website http://www.segmentmeifyoucan.com/

Access Paper or Ask Questions

Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

Apr 12, 2021
Kaicheng Yu, Rene Ranftl, Mathieu Salzmann

Figure 1 for Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

Figure 2 for Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

Figure 3 for Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

Figure 4 for Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

* Accepted to CVPR 2021

Access Paper or Ask Questions

Robust Differentiable SVD

Apr 08, 2021
Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann

Figure 1 for Robust Differentiable SVD

Figure 2 for Robust Differentiable SVD

Figure 3 for Robust Differentiable SVD

Figure 4 for Robust Differentiable SVD

* IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021
* IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) PREPRINT 2021

Access Paper or Ask Questions

Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

Dec 30, 2020
Krishna Kanth Nakka, Mathieu Salzmann

Figure 1 for Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

Figure 2 for Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

Figure 3 for Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

Figure 4 for Temporally-Transferable Perturbations: Efficient, One-Shot Adversarial Attacks for Online Visual Object Trackers

Access Paper or Ask Questions