9 citations · 50 across the 17 of their papers we have counts for
21 papers
Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient Matching
Cangxiong Chen, Neill D. F. Campbell
Recent works have demonstrated that it is possible to reconstruct training images and their labels from gradients of an image-classification model when its architecture is known. U…
Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
Margaret Duff, Ivor J. A. Simpson, Matthias J. Ehrhardt +1
Objective: This paper investigates how generative models, trained on ground-truth images, can be used \changes{as} priors for inverse problems, penalizing reconstructions far from…
Learning Structured Gaussians to Approximate Deep Ensembles
Ivor J. A. Simpson, Sara Vicente, Neill D. F. Campbell
This paper proposes using a sparse-structured multivariate Gaussian to provide a closed-form approximator for the output of probabilistic ensemble models used for dense image predi…
Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classification
Cangxiong Chen, Neill D. F. Campbell
Federated learning of deep learning models for supervised tasks, e.g. image classification and segmentation, has found many applications: for example in human-in-the-loop tasks suc…
Aligned Multi-Task Gaussian Process
Olga Mikheeva, Ieva Kazlauskaite, Adam Hartshorne +3
Multi-task learning requires accurate identification of the correlations between tasks. In real-world time-series, tasks are rarely perfectly temporally aligned; traditional multi-…
Regularising Inverse Problems with Generative Machine Learning Models
Margaret Duff, Neill D. F. Campbell, Matthias J. Ehrhardt
Deep neural network approaches to inverse imaging problems have produced impressive results in the last few years. In this paper, we consider the use of generative models in a vari…
Black-box density function estimation using recursive partitioning
Erik Bodin, Zhenwen Dai, Neill D. F. Campbell +1
We present a novel approach to Bayesian inference and general Bayesian computation that is defined through a sequential decision loop. Our method defines a recursive partitioning o…
DiverseNet: When One Right Answer is not Enough
Michael Firman, Neill D. F. Campbell, Lourdes Agapito +1
Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is s…
Compositional uncertainty in deep Gaussian processes
Ivan Ustyuzhaninov, Ieva Kazlauskaite, Markus Kaiser +3
Gaussian processes (GPs) are nonparametric priors over functions. Fitting a GP implies computing a posterior distribution of functions consistent with the observed data. Similarly,…
Modulating Surrogates for Bayesian Optimization
Erik Bodin, Markus Kaiser, Ieva Kazlauskaite +3
Bayesian optimization (BO) methods often rely on the assumption that the objective function is well-behaved, but in practice, this is seldom true for real-world objectives even if…
Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation
Alessandro Di Martino, Erik Bodin, Carl Henrik Ek +1
The shape of an object is an important characteristic for many vision problems such as segmentation, detection and tracking. Being independent of appearance, it is possible to gene…
Sequence Alignment with Dirichlet Process Mixtures
Ieva Kazlauskaite, Ivan Ustyuzhaninov, Carl Henrik Ek +1
We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM). We follow the approach in…
The GAN that Warped: Semantic Attribute Editing with Unpaired Data
Gara Dorta, Sara Vicente, Neill D. F. Campbell +1
Deep neural networks have recently been used to edit images with great success, in particular for faces. However, they are often limited to only being able to work at a restricted…
DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures
Andrew R. Lawrence, Carl Henrik Ek, Neill D. F. Campbell
We present a non-parametric Bayesian latent variable model capable of learning dependency structures across dimensions in a multivariate setting. Our approach is based on flexible…
Training VAEs Under Structured Residuals
Gara Dorta, Sara Vicente, Lourdes Agapito +2
Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized likelihood model, whereby the output uncertainty…
Structured Uncertainty Prediction Networks
Gara Dorta, Sara Vicente, Lourdes Agapito +2
This paper is the first work to propose a network to predict a structured uncertainty distribution for a synthesized image. Previous approaches have been mostly limited to predicti…
Gaussian Process Latent Variable Alignment Learning
Ieva Kazlauskaite, Carl Henrik Ek, Neill D. F. Campbell
We present a model that can automatically learn alignments between high-dimensional data in an unsupervised manner. Our proposed method casts alignment learning in a framework wher…
Nonparametric Inference for Auto-Encoding Variational Bayes
Erik Bodin, Iman Malik, Carl Henrik Ek +1
We would like to learn latent representations that are low-dimensional and highly interpretable. A model that has these characteristics is the Gaussian Process Latent Variable Mode…
Latent Gaussian Process Regression
Erik Bodin, Neill D. F. Campbell, Carl Henrik Ek
We introduce Latent Gaussian Process Regression which is a latent variable extension allowing modelling of non-stationary multi-modal processes using GPs. The approach is built on…
Responsive Action-based Video Synthesis
Corneliu Ilisescu, Halil Aytac Kanaci, Matteo Romagnoli +2
We propose technology to enable a new medium of expression, where video elements can be looped, merged, and triggered, interactively. Like audio, video is easy to sample from the r…
Hierarchical Subquery Evaluation for Active Learning on a Graph
Oisin Mac Aodha, Neill D. F. Campbell, Jan Kautz +1
To train good supervised and semi-supervised object classifiers, it is critical that we not waste the time of the human experts who are providing the training labels. Existing acti…