IAM

PUBLICATIONSBYYEAR

2019

David Stutz, Matthias Hein, Bernt Schiele.
Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training.
ArXiv, 2019.
[ArXiv | BibTeX | Project Page]

David Stutz, Matthias Hein, Bernt Schiele.
Disentangling Adversarial Robustness and Generalization.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[ArXiv | BibTeX | Project Page]

2018

David Stutz, Andreas Geiger.
Learning 3D Shape Completion under Weak Supervision.
International Journal of Computer Vision, 2018.
[DOI | ArXiv | BibTeX | Project Page]

David Stutz, Andreas Geiger.
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
[PDF | BibTeX | Project Page]

David Stutz, Alexander Hermans, Bastian Leibe.
Superpixels: an evaluation of the state-of-the-art.
Computer Vision and Image Understanding, Volume 166, 2018.
[DOI | ArXiv | PDF | BibTeX | Project Page]

2015

David Stutz.
Superpixel segmentation: an evaluation.
German Conference on Pattern Recognition, 2015.
[PDF | BibTeX | Project Page]

RELATEDARTICLESANDPROJECTS

Articles and project pages related to the publications listed above. Also see Projects for an overview as well as THESES and SEMINAR PAPERS .

ARTICLE

ArXiv Pre-Print “Confidence-Calibrated Adversarial Training”

Adversarial training is the de-facto standard to obtain models robust against adversarial examples. However, on complex datasets, a significant loss in accuracy is incurred and the robustness does not generalize to attacks not used during training. This paper introduces confidence-calibrated adversarial training. By forcing the confidence on adversarial examples to decay with their distance to the training data, the loss in accuracy is reduced and robustness generalizes to other attacks and larger perturbations.

More ...

16thOCTOBER2019

PROJECT

Confidence calibration of adversarial training for “generalizable” robustness.

More ...

ARTICLE

CVPR Paper “Disentangling Adversarial Robustness and Generalization”

Our paper on adversarial robustness and generalization was accepted at CVPR’19. In the revised paper, we show that adversarial examples usually leave the manifold, including a brief theoretical argumentation. Similarly, adversarial examples can be found on the manifold; then, robustness is nothing else than generalization. For (off-manifold) adversarial examples, in contrast, we show that generalization and robustness are not necessarily contradicting objectives. As example, on synthetic data, we adversarially train a robust and accurate model. This article gives a short abstract and provides the paper including appendix.

More ...

04thDECEMBER2018

PROJECT

Disentangling the relationship between adversarial robustness and generalization.

More ...

ARTICLE

ArXiv Pre-Print “Disentangling Adversarial Robustness and Generalization”

To date, it is unclear whether we can obtain both accurate and robust deep networks — meaning deep networks that generalize well and resist adversarial examples. In this pre-print, we aim to disentangle the relationship between adversarial robustness and generalization. The paper is available on ArXiv.

More ...

ARTICLE

IJCV Paper “Learning 3D Shape Completion under Weak Supervision”

Our CVPR’18 follow-up paper has been accepted at IJCV. In this longer paper we extend our weakly-supervised 3D shape completion approach to obtain high-quality shape predictions, and also present updated, synthetic benchmarks on ShapeNet and ModelNet. The paper is available through Springer Link and ArXiv.

More ...

ARTICLE

ArXiv Pre-Print “Learning 3D Shape Completion under Weak Supervision”

In this follow-up on our CVPR’18 work, we extend our weakly-supervised 3D shape completion approach to obtain high-quality shape predictions, and also present updated, synthetic benchmarks on ShapeNet and ModelNet. The paper is now available as pre-print on ArXiv. Abstract, some experimental results and a comparison to our CVPR’18 work can be found in this article.

More ...

19thMAY2018

PROJECT

Learning 3D shape completion under weak supervision; on ShapeNet, ModelNet, KITTI and Kinect data; published at CVPR and on ArXiv.

More ...

ARTICLE

CVPR’18 Paper “Learning 3D Shape Completion from Laser Scan Data with Weak Supervision”

In this CVPR’18 paper, based on my master thesis, we propose a weakly-supervised and learning-based approach to 3D shape completion of sparse and noisy point clouds. We show that, using a learned shape prior, shape completion can be learned without access to ground truth shapes — only by knowing the object category at hand. This article provides the paper and its supplementary material.

More ...

17thDECEMBER2017

PROJECT

Weakly-supervised shape completion of cars on KITTI using variational auto-encoders; including two synthetic ShapeNet-based benchmark datasets.

More ...