activity
20242026
collaborators

5 papers

cs.LG2026

Improving Adversarial Robustness of Attribution via Implicit Regularization

Amir Mehrpanah, Matteo Gamba, Hossein Azizpour

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expe…

cs.CV2026

Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning

Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour +1

We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on partially labeled datasets with di…

cs.LG2025

On Spectral Properties of Gradient-based Explanation Methods

Amir Mehrpanah, Erik Englesson, Hossein Azizpour

Understanding the behavior of deep networks is crucial to increase our confidence in their results. Despite an extensive body of work for explaining their predictions, researchers…

cs.LG2025

On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations

Amir Mehrpanah, Matteo Gamba, Kevin Smith +1

ReLU networks, while prevalent for visual data, have sharp transitions, sometimes relying on individual pixels for predictions, making vanilla gradient-based explanations noisy and…

cs.CV2024

Medical Image Segmentation with SAM-generated Annotations

Iira Häkkinen, Iaroslav Melekhov, Erik Englesson +2

The field of medical image segmentation is hindered by the scarcity of large, publicly available annotated datasets. Not all datasets are made public for privacy reasons, and creat…