Max Maria Losch

According to our database, Max Maria Losch authored at least 6 papers between 2019 and 2024.

Collaborative distances:

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

2024

Improving trustworthiness of deep learning via inspectable and robust representations.

Max Maria Losch

PhD thesis, 2024

On Adversarial Training without Perturbing all Examples.

Max Maria Losch, Mohamed Omran, David Stutz, Mario Fritz, Bernt Schiele

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Certified Robust Models with Slack Control and Large Lipschitz Constants.

Max Maria Losch, David Stutz, Bernt Schiele, Mario Fritz

Proceedings of the Pattern Recognition - 45th DAGM German Conference, 2023

2020

Semantic Bottlenecks: Quantifying and Improving Inspectability of Deep Representations.

Max Maria Losch, Mario Fritz, Bernt Schiele

Proceedings of the Pattern Recognition - 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28, 2020

Analyzing the Dependency of ConvNets on Spatial Information.

Yue Fan, Yongqin Xian, Max Maria Losch, Bernt Schiele

Proceedings of the Pattern Recognition - 42nd DAGM German Conference, DAGM GCPR 2020, Tübingen, Germany, September 28, 2020

2019

Interpretability Beyond Classification Output: Semantic Bottleneck Networks.

Max Maria Losch, Mario Fritz, Bernt Schiele

CoRR, 2019