Search Results - "Dombrowski, Mischa"

Data-Centric Benchmarking of Neural Network Architectures for the Univariate Time Series Forecasting Task by Schlieper, Philipp, Dombrowski, Mischa, Nguyen, An, Zanca, Dario, Eskofier, Bjoern

“…Time series forecasting has witnessed a rapid proliferation of novel neural network approaches in recent times. However, performances in terms of benchmarking…”
Get full text

Quantifying Sample Anonymity in Score-Based Generative Models with Adversarial Fingerprinting by Dombrowski, Mischa, Kainz, Bernhard

“…Recent advances in score-based generative models have led to a huge spike in the development of downstream applications using generative models ranging from…”
Get full text

Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification by Dombrowski, Mischa, Reynaud, Hadrien, Kainz, Bernhard

“…Latent Video Diffusion Models can easily deceive casual observers and domain experts alike thanks to the produced image quality and temporal consistency…”
Get full text

Image Generation Diversity Issues and How to Tame Them by Dombrowski, Mischa, Zhang, Weitong, Cechnicka, Sarah, Reynaud, Hadrien, Kainz, Bernhard

“…Generative methods now produce outputs nearly indistinguishable from real data but often fail to fully capture the data distribution. Unlike quality issues,…”
Get full text

JVID: Joint Video-Image Diffusion for Visual-Quality and Temporal-Consistency in Video Generation by Reynaud, Hadrien, Baugh, Matthew, Dombrowski, Mischa, Cechnicka, Sarah, Meng, Qingjie, Kainz, Bernhard

“…We introduce the Joint Video-Image Diffusion model (JVID), a novel approach to generating high-quality and temporally coherent videos. We achieve this by…”
Get full text

Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models by Dombrowski, Mischa, Reynaud, Hadrien, Baugh, Matthew, Kainz, Bernhard

“…Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has…”
Get full text

EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing by Reynaud, Hadrien, Meng, Qingjie, Dombrowski, Mischa, Ghosh, Arijit, Day, Thomas, Gomez, Alberto, Leeson, Paul, Kainz, Bernhard

“…To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of…”
Get full text

Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis by Reynaud, Hadrien, Qiao, Mengyun, Dombrowski, Mischa, Day, Thomas, Razavi, Reza, Gomez, Alberto, Leeson, Paul, Kainz, Bernhard

“…Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model…”
Get full text

Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks by Baugh, Matthew, Tan, Jeremy, Müller, Johanna P, Dombrowski, Mischa, Batten, James, Kainz, Bernhard

“…There is a growing interest in single-class modelling and out-of-distribution detection as fully supervised machine learning models cannot reliably identify…”
Get full text

Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability by Dombrowski, Mischa, Reynaud, Hadrien, Müller, Johanna P, Baugh, Matthew, Kainz, Bernhard

“…Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of…”
Get full text

Confidence-Aware and Self-Supervised Image Anomaly Localisation by Müller, Johanna P, Baugh, Matthew, Tan, Jeremy, Dombrowski, Mischa, Kainz, Bernhard

“…Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected…”
Get full text

D'ARTAGNAN: Counterfactual Video Generation by Reynaud, Hadrien, Vlontzos, Athanasios, Dombrowski, Mischa, Lee, Ciarán, Beqiri, Arian, Leeson, Paul, Kainz, Bernhard

“…Causally-enabled machine learning frameworks could help clinicians to identify the best course of treatments by answering counterfactual questions. We explore…”
Get full text