33 citations · 39 across the 20 of their papers we have counts for
22 papers
Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters
Felix Nützel, Mischa Dombrowski, Luca Hagen +1
Pretrained latent spaces trade compression, reconstruction, and the learnability of the coordinates a downstream generator has to work in, which complicates adapting these spaces t…
A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging
Mischa Dombrowski, Bernhard Kainz
Diffusion-based synthetic data generation offers a promising route for sharing medical imaging data without releasing sensitive patient records. However, generative models face a f…
The Learnability Gap in Medical Latent Diffusion
Mischa Dombrowski, Felix Nützel, Bernhard Kainz
Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fide…
Flow Matching with Optimized Subclass Priors for Medical Image Augmentation
Felix Nützel, Mischa Dombrowski, Bernhard Kainz
Rare diseases dominate the diagnostic challenge in medical imaging yet are severely underrepresented in clinical datasets, causing classifiers to fail on exactly the conditions whe…
LCMem: A Universal Model for Robust Image Memorization Detection
Mischa Dombrowski, Felix Nützel, Bernhard Kainz
Recent advances in generative image modeling have achieved visual realism sufficient to deceive human experts, yet their potential for privacy preserving data sharing remains insuf…
GRASP: Guided Residual Adapters with Sample-wise Partitioning
Felix Nützel, Mischa Dombrowski, Bernhard Kainz
Text-to-image flow matching transformers degrade sharply in long-tail settings: tail-class outputs collapse in fidelity and diversity, limiting their value as synthetic augmentatio…
Graph Conditioned Diffusion for Controllable Histopathology Image Generation
Sarah Cechnicka, Matthew Baugh, Weitong Zhang +5
Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sen…
Ontology-Based Concept Distillation for Radiology Report Retrieval and Labeling
Felix Nützel, Mischa Dombrowski, Bernhard Kainz
Retrieval-augmented learning based on radiology reports has emerged as a promising direction to improve performance on long-tail medical imaging tasks, such as rare disease detecti…
Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models
Felix Nützel, Mischa Dombrowski, Bernhard Kainz
Phrase grounding, i.e., mapping natural language phrases to specific image regions, holds significant potential for disease localization in medical imaging through clinical reports…
Enabling PSO-Secure Synthetic Data Sharing Using Diversity-Aware Diffusion Models
Mischa Dombrowski, Bernhard Kainz
Synthetic data has recently reached a level of visual fidelity that makes it nearly indistinguishable from real data, offering great promise for privacy-preserving data sharing in…
Video Dataset Condensation with Diffusion Models
Zhe Li, Hadrien Reynaud, Mischa Dombrowski +3
In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, bot…
Image Generation Diversity Issues and How to Tame Them
Mischa Dombrowski, Weitong Zhang, Sarah Cechnicka +2
Generative methods now produce outputs nearly indistinguishable from real data but often fail to fully capture the data distribution. Unlike quality issues, diversity limitations i…
Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification
Mischa Dombrowski, Hadrien Reynaud, Bernhard Kainz
Latent Video Diffusion Models can easily deceive casual observers and domain experts alike thanks to the produced image quality and temporal consistency. Beyond entertainment, this…
JVID: Joint Video-Image Diffusion for Visual-Quality and Temporal-Consistency in Video Generation
Hadrien Reynaud, Matthew Baugh, Mischa Dombrowski +3
We introduce the Joint Video-Image Diffusion model (JVID), a novel approach to generating high-quality and temporally coherent videos. We achieve this by integrating two diffusion…
EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing
Hadrien Reynaud, Qingjie Meng, Mischa Dombrowski +5
To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imag…
Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks
Matthew Baugh, Jeremy Tan, Johanna P. Müller +3
There is a growing interest in single-class modelling and out-of-distribution detection as fully supervised machine learning models cannot reliably identify classes not included in…
Quantifying Sample Anonymity in Score-Based Generative Models with Adversarial Fingerprinting
Mischa Dombrowski, Bernhard Kainz
Recent advances in score-based generative models have led to a huge spike in the development of downstream applications using generative models ranging from data augmentation over…
Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability
Mischa Dombrowski, Hadrien Reynaud, Johanna P. Müller +2
Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-train…
Confidence-Aware and Self-Supervised Image Anomaly Localisation
Johanna P. Müller, Matthew Baugh, Jeremy Tan +2
Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class…
Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis
Hadrien Reynaud, Mengyun Qiao, Mischa Dombrowski +5
Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, ca…
Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models
Mischa Dombrowski, Hadrien Reynaud, Matthew Baugh +1
Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has been given a significa…
D'ARTAGNAN: Counterfactual Video Generation
Hadrien Reynaud, Athanasios Vlontzos, Mischa Dombrowski +4
Causally-enabled machine learning frameworks could help clinicians to identify the best course of treatments by answering counterfactual questions. We explore this path for the cas…