Lukas Ruff — accepted AI-conference papers

2023

DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology

Marco Aversa, Gabriel Nobis, Miriam Hägele, Kai Standvoss, Mihaela Chirica, Roderick Murray-Smith +7

NeurIPS 2023spotlight

We present DiffInfinite, a hierarchical diffusion model that generates arbitrarily large histological images while preserving long-range correlation structural information. Our approach first generates synthetic segmentation masks, subsequently used as conditions for the high-fidelity generative dif…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗

2021

Explainable Deep One-Class Classification

Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Marius Kloft, Klaus Robert Muller

ICLR 2021poster

Deep one-class classification variants for anomaly detection learn a mapping that concentrates nominal samples in feature space causing anomalies to be mapped away. Because this transformation is highly non-linear, finding interpretations poses a significant challenge. In this paper we present an ex…

Cited by 297 Source ↗PDF ↗code ↗Scholar ↗

2021

Transfer-Based Semantic Anomaly Detection

Lucas Deecke, Lukas Ruff, Robert A. Vandermeulen, Hakan Bilen

ICML 2021spotlight

Detecting semantic anomalies is challenging due to the countless ways in which they may appear in real-world data. While enhancing the robustness of networks may be sufficient for modeling simplistic anomalies, there is no good known way of preparing models for all potential and unseen anomalies tha…

Cited by 48 Source ↗PDF ↗Scholar ↗

2020

Deep Semi-Supervised Anomaly Detection

Lukas Ruff, Robert A. Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller +1

ICLR 2020poster

Deep approaches to anomaly detection have recently shown promising results over shallow methods on large and complex datasets. Typically anomaly detection is treated as an unsupervised learning problem. In practice however, one may have---in addition to a large set of unlabeled samples---access to a…

Cited by 824 Source ↗code ↗Scholar ↗

2018

Deep One-Class Classification

Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder +2

ICML 2018oral

Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection. Those approaches which do exist involve networks trained to perform a task other than anomaly detection, namely generative models or compr…

Cited by 2927 Source ↗PDF ↗code ↗Scholar ↗