Kira Maag

According to our database, Kira Maag authored at least 16 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Integrating uncertainty quantification into randomized smoothing based robustness guarantees.

Sina Däubener, Kira Maag, David Krueger, Asja Fischer

CoRR, 2024

Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis.

Kira Maag, Roman Resner, Asja Fischer

CoRR, 2024

Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation.

Kira Maag, Asja Fischer

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Pixel-Wise Gradient Uncertainty for Convolutional Neural Networks Applied to Out-of-Distribution Segmentation.

Kira Maag, Tobias Riedlinger

Proceedings of the 19th International Joint Conference on Computer Vision, 2024

Uncertainty-Based Detection of Adversarial Attacks in Semantic Segmentation.

Kira Maag, Asja Fischer

Proceedings of the 19th International Joint Conference on Computer Vision, 2024

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion.

Edgar Heinert, Matthias Rottmann, Kira Maag, Karsten Kahl

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

Detection of Iterative Adversarial Attacks via Counter Attack.

Matthias Rottmann, Kira Maag, Mathis Peyron, Hanno Gottschalk, Natasa Krejic

J. Optim. Theory Appl., September, 2023

False Negative Reduction in Semantic Segmentation Under Domain Shift Using Depth Estimation.

Kira Maag, Matthias Rottmann

Proceedings of the 18th International Joint Conference on Computer Vision, 2023

2022

Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects.

Kira Maag, Robin Chan, Svenja Uhlemeyer, Kamil Kowol, Hanno Gottschalk

Proceedings of the Computer Vision - ACCV 2022, 2022

2021

Prediction Rating and Performance Improvement for Segmentation Networks by Time-Dynamic Uncertainty Estimates.

Kira Maag

PhD thesis, 2021

Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates.

Kira Maag, Matthias Rottmann, Serin Varghese, Fabian Hüger, Peter Schlicht, Hanno Gottschalk

Proceedings of the International Joint Conference on Neural Networks, 2021

False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates.

Kira Maag

Proceedings of the 33rd IEEE International Conference on Tools with Artificial Intelligence, 2021

An Unsupervised Temporal Consistency (TC) Loss To Improve the Performance of Semantic Segmentation Networks.

Serin Varghese, Sharat Gujamagadi, Marvin Klingner, Nikhil Kapoor, Andreas Bär, Jan David Schneider, Kira Maag, Peter Schlicht, Fabian Hüger, Tim Fingscheidt

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

2020

Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates.

Kira Maag, Matthias Rottmann, Fabian Hüger, Peter Schlicht, Hanno Gottschalk

CoRR, 2020

Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks.

Kira Maag, Matthias Rottmann, Hanno Gottschalk

Proceedings of the 32nd IEEE International Conference on Tools with Artificial Intelligence, 2020

Detection of False Positive and False Negative Samples in Semantic Segmentation.

Matthias Rottmann, Kira Maag, Robin Chan, Fabian Hüger, Peter Schlicht, Hanno Gottschalk

Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition, 2020