Sotabase
Home
Researchers
Career
·
PhD Student
,
Technical University of Munich
2025–
·
Postdoctoral Researcher in Machine Learning and Computer Vision
,
University of Oxford
2025–
Publications
(34)
On the reproducibility of expert-operated and robotic ultrasound acquisitions
International Journal of Computer Assisted Radiology and Surgery · 2017
69
cited
Latent Guard: a Safety Framework for Text-to-image Generation
European Conference on Computer Vision · 2024
56
cited
A Survey on Transferability of Adversarial Examples across Deep Neural Networks
Trans. Mach. Learn. Res. · 2023
52
cited
Neural Response Interpretation through the Lens of Critical Pathways
Computer Vision and Pattern Recognition · 2021
41
cited
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
Neural Information Processing Systems · 2021
33
cited
CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN
arXiv.org · 2022
29
cited
Do Explanations Explain? Model Knows Best
Computer Vision and Pattern Recognition · 2022
28
cited
Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation
BrainLes@MICCAI · 2020
23
cited
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features
International Conference on Medical Image Computing and Computer-Assisted Intervention · 2021
17
cited
FlexR: Few-shot Classification with Language Embeddings for Structured Reporting of Chest X-rays
International Conference on Medical Imaging with Deep Learning · 2022
15
cited
Learning Interpretable Features via Adversarially Robust Optimization
International Conference on Medical Image Computing and Computer-Assisted Intervention · 2019
15
cited
Improving Feature Attribution through Input-specific Network Pruning
2019
13
cited
Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models
International Conference on Medical Image Computing and Computer-Assisted Intervention · 2021
13
cited
Mixture of Experts Made Intrinsically Interpretable
International Conference on Machine Learning · 2025
12
cited
Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images
Information Processing in Medical Imaging · 2023
12
cited
Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
2024
12
cited
Learnable Sparsity for Vision Generative Models
2024
11
cited
AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
2024
9
cited
Explaining Neural Networks via Perturbing Important Learned Features
arXiv.org · 2019
9
cited
Learning Visual Prompts for Guiding the Attention of Vision Transformers
arXiv.org · 2024
9
cited
Show all 34 papers →
Sotabase
Ashkan Khakzar | Researcher Profile | Sotabase | Sotabase