297 citations · 1.5k across the 199 of their papers we have counts for
35 papers · 1 filter
The curious case of the test set AUROC
Michael Roberts, Alon Hazan, Sören Dittmer +2
Whilst the size and complexity of ML models have rapidly and significantly increased over the past decade, the methods for assessing their performance have not kept pace. In partic…
TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios
Lihao Liu, Yanqi Cheng, Zhongying Deng +6
Multi-object tracking in traffic videos is a crucial research area, offering immense potential for enhancing traffic monitoring accuracy and promoting road safety measures through…
Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation
Teo Deveney, Jan Stanczuk, Lisa Maria Kreusser +2
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling, due to their state-of-the art performance in many generation tasks…
TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations
Zhenda Shen, Yanqi Cheng, Raymond H. Chan +3
Implicit neural representations (INRs) have garnered significant interest recently for their ability to model complex, high-dimensional data without explicit parameterisation. In t…
Traffic Video Object Detection using Motion Prior
Lihao Liu, Yanqi Cheng, Dongdong Chen +4
Traffic videos inherently differ from generic videos in their stationary camera setup, thus providing a strong motion prior where objects often move in a specific direction over a…
Provably Convergent Data-Driven Convex-Nonconvex Regularization
Zakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee +1
An emerging new paradigm for solving inverse problems is via the use of deep learning to learn a regularizer from data. This leads to high-quality results, but often at the cost of…
Single-Shot Plug-and-Play Methods for Inverse Problems
Yanqi Cheng, Lipei Zhang, Zhenda Shen +5
The utilisation of Plug-and-Play (PnP) priors in inverse problems has become increasingly prominent in recent years. This preference is based on the mathematical equivalence betwee…
Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
Moshe Eliasof, Davide Murari, Ferdia Sherry +1
Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain susceptible to inp…
Recent Methodological Advances in Federated Learning for Healthcare
Fan Zhang, Daniel Kreuter, Yichen Chen +10
For healthcare datasets, it is often not possible to combine data samples from multiple sites due to ethical, privacy or logistical concerns. Federated learning allows for the util…
The Missing U for Efficient Diffusion Models
Sergio Calvo-Ordonez, Chun-Wun Cheng, Jiahao Huang +4
Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields reco…
MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening
Yijun Yang, Shujun Wang, Lihao Liu +4
Breast cancer is a major cause of cancer death among women, emphasising the importance of early detection for improved treatment outcomes and quality of life. Mammography, the prim…
Riemannian geometry for efficient analysis of protein dynamics data
Willem Diepeveen, Carlos Esteve-Yagüe, Jan Lellmann +2
An increasingly common viewpoint is that protein dynamics data sets reside in a non-linear subspace of low conformational energy. Ideal data analysis tools for such data sets shoul…
Boosting Data-Driven Mirror Descent with Randomization, Equivariance, and Acceleration
Hong Ye Tan, Subhadip Mukherjee, Junqi Tang +1
Learning-to-optimize (L2O) is an emerging research area in large-scale optimization with applications in data science. Recently, researchers have proposed a novel L2O framework cal…
Reinterpreting survival analysis in the universal approximator age
Sören Dittmer, Michael Roberts, Jacobus Preller +4
Survival analysis is an integral part of the statistical toolbox. However, while most domains of classical statistics have embraced deep learning, survival analysis only recently g…
Convergent regularization in inverse problems and linear plug-and-play denoisers
Andreas Hauptmann, Subhadip Mukherjee, Carola-Bibiane Schönlieb +1
Plug-and-play (PnP) denoising is a popular iterative framework for solving imaging inverse problems using off-the-shelf image denoisers. Their empirical success has motivated a lin…
Inverse Evolution Layers: Physics-informed Regularizers for Deep Neural Networks
Chaoyu Liu, Zhonghua Qiao, Chao Li +1
Traditional image processing methods employing partial differential equations (PDEs) offer a multitude of meaningful regularizers, along with valuable theoretical foundations for a…
CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
Jiahao Huang, Angelica Aviles-Rivero, Carola-Bibiane Schönlieb +1
Deep learning has shown the capability to substantially accelerate MRI reconstruction while acquiring fewer measurements. Recently, diffusion models have gained burgeoning interest…
Proximal Langevin Sampling With Inexact Proximal Mapping
Matthias J. Ehrhardt, Lorenz Kuger, Carola-Bibiane Schönlieb
In order to solve tasks like uncertainty quantification or hypothesis tests in Bayesian imaging inverse problems, we often have to draw samples from the arising posterior distribut…
Designing Stable Neural Networks using Convex Analysis and ODEs
Ferdia Sherry, Elena Celledoni, Matthias J. Ehrhardt +3
Motivated by classical work on the numerical integration of ordinary differential equations we present a ResNet-styled neural network architecture that encodes non-expansive (1-Lip…
Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
Georgios Batzolis, Jan Stanczuk, Carola-Bibiane Schönlieb
As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeabl…
Deep Learning-based Diffusion Tensor Cardiac Magnetic Resonance Reconstruction: A Comparison Study
Jiahao Huang, Pedro F. Ferreira, Lichao Wang +11
In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the micro-structure of myocardial tissue in the living hear…
A sparse optimization approach to infinite infimal convolution regularization
Kristian Bredies, Marcello Carioni, Martin Holler +2
In this paper we introduce the class of infinite infimal convolution functionals and apply these functionals to the regularization of ill-posed inverse problems. The proposed regul…
NF-ULA: Langevin Monte Carlo with Normalizing Flow Prior for Imaging Inverse Problems
Ziruo Cai, Junqi Tang, Subhadip Mukherjee +3
Bayesian methods for solving inverse problems are a powerful alternative to classical methods since the Bayesian approach offers the ability to quantify the uncertainty in the solu…
Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels
Jan Oscar Cross-Zamirski, Praveen Anand, Guy Williams +3
Image-to-image reconstruction problems with free or inexpensive metadata in the form of class labels appear often in biological and medical image domains. Existing text-guided or s…