Jan Macdonald

Jan Macdonald

Auto-generated profile, based on publicly available information

Jan Macdonald

Institut für Mathematik Technische Universität Berlin

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 February 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MGMartin Genzel
Martin Genzel
JMJan Macdonald
Jan Macdonald
MMMaximilian Marz
Maximilian Marz
In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability appears mandatory. Recent works have pointed out instabilities of deep neural networks for several image reconstruction tasks. In analogy to adversarial attacks in classification, it was shown that slight distortions in the input domain may cause severe artifacts. The present article sheds new light on this concern, by conducting an extensive study of the robustness of deep-learning-based algorithms for solving underdetermined inverse problems. This covers compressed sensing with Gaussian measurements as well as image recovery from Fourier and Radon measurements, including a real-world scenario for magnetic resonance imaging (using the NYU-fastMRI dataset). Our main focus is on computing adversarial perturbations of the measurements that maximize the reconstruction error. A distinctive feature of our approach is the quantitative and qualitative comparison with total-variation minimization, which serves as a provably robust reference method. In contrast to previous findings, our results reveal that standard end-to-end network architectures are not only resilient against statistical noise, but also against adversarial perturbations. All considered networks are trained by common deep learning techniques, without sophisticated defense strategies.

4 September 2021 in International Journal of Computer Assisted Radiology and Surgery
Verified
Journal Article
Open access
PDF file
LOLuis Oala
Luis Oala
CHCosmas Heiß
Cosmas Heiß
JMJan Macdonald
Jan Macdonald
MMMaximilian März
Maximilian März
GKGitta Kutyniok
Gitta Kutyniok
WSWojciech Samek
Wojciech Samek
Purpose: The quantitative detection of failure modes is important for making deep neural networks reliable and usable at scale. We consider three examples for common failure modes in image reconstruction and demonstrate the potential of uncertainty quantification as a fine-grained alarm system. Methods: We propose a deterministic, modular and lightweight approach called Interval Neural Network (INN) that produces fast and easy to interpret uncertainty scores for deep neural networks. Importantly, INNs can be constructed post hoc for already trained prediction networks. We compare it against state-of-the-art baseline methods (MCDrop, ProbOut). Results: We demonstrate on controlled, synthetic inverse problems the capacity of INNs to capture uncertainty due to noise as well as directional error information. On a real-world inverse problem with human CT scans, we can show that INNs produce uncertainty scores which improve the detection of all considered failure modes compared to the baseline methods. Conclusion: Interval Neural Networks offer a promising tool to expose weaknesses of deep image reconstruction models and ultimately make them more reliable. The fact that they can be applied post hoc to equip already trained deep neural network models with uncertainty scores makes them particularly interesting for deployment.

2 September 2017 in Journal of Mathematical Imaging and Vision
Verified
Journal Article
Closed access
PDF file
JMJan Macdonald
Jan Macdonald
LRLars Ruthotto
Lars Ruthotto

19 February 2026 in ISPRS Open Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Open access
JRJoana Reuss
Joana Reuss
JMJan Macdonald
Jan Macdonald
SBSimon Becker
Simon Becker
EGEkaterina Gikalo
Ekaterina Gikalo
KSKonrad Schultka
Konrad Schultka
MKMarco Körner
Marco Körner

1 January 2023 in Inverse Problems and Imaging
Verified
Journal Article
Closed access
PDF file
TTTheophil Trippe
Theophil Trippe
MGMartin Genzel
Martin Genzel
JMJan Macdonald
Jan Macdonald
MMMaximilian Marz
Maximilian Marz
This work presents a novel deep-learning-based pipeline for the inverse problem of image deblurring, leveraging augmentation and pre-training with synthetic data. Our results build on our winning submission to the recent Helsinki Deblur Challenge 2021, whose goal was to explore the limits of state-of-the-art deblurring algorithms in a real-world data setting. The task of the challenge was to deblur out-of-focus images of random text, thereby in a downstream task, maximizing an optical-character-recognition-based score function. A key step of our solution is the data-driven estimation of the physical forward model describing the blur process. This enables a stream of synthetic data, generating pairs of ground-truth and blurry images on-the-fly, which is used for an extensive augmentation of the small amount of challenge data provided. The actual deblurring pipeline consists of an approximate inversion of the radial lens distortion (determined by the estimated forward model) and a U-Net architecture, which is trained end-to-end. Our algorithm was the only one passing the hardest challenge level, achieving over $ 70\% $ character recognition accuracy. Our findings are well in line with the paradigm of data-centric machine learning, and we demonstrate its effectiveness in the context of inverse problems. Apart from a detailed presentation of our methodology, we also analyze the importance of several design choices in a series of ablation studies. The code of our challenge submission is available under https://github.com/theophil-trippe/HDC_TUBerlin_version_1.

27 February 2021
Verified
Book Chapter
Closed access
PDF file
JMJan Macdonald
Jan Macdonald
MMMaximilian März
Maximilian März
LOLuis Oala
Luis Oala
WSWojciech Samek
Wojciech Samek