• Publications
  • Influence
The Pascal Visual Object Classes Challenge: A Retrospective
A review of the Pascal Visual Object Classes challenge from 2008-2012 and an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges. Expand
Conditional Neural Processes
Conditional Neural Processes are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks and trained via gradient descent, yet scale to complex functions and large datasets. Expand
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural networkExpand
Emergence of Locomotion Behaviours in Rich Environments
This paper explores how a rich environment can help to promote the learning of complex behavior, and finds that this encourages the emergence of robust behaviours that perform well across a suite of tasks. Expand
Data-Efficient Image Recognition with Contrastive Predictive Coding
This work revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations which make the variability in natural signals more predictable, and produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. Expand
Attentive Neural Processes
Attention is incorporated into NPs, allowing each input location to attend to the relevant context points for the prediction, which greatly improves the accuracy of predictions, results in noticeably faster training, and expands the range of functions that can be modelled. Expand
A Probabilistic U-Net for Segmentation of Ambiguous Images
A generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses and reproduces the possible segmentation variants as well as the frequencies with which they occur significantly better than published approaches. Expand
Neural Processes
This work introduces a class of neural latent variable models which it calls Neural Processes (NPs), combining the best of both worlds: probabilistic, data-efficient and flexible, however they are also computationally intensive and thus limited in their applicability. Expand
Unsupervised Learning of 3D Structure from Images
This paper learns strong deep generative models of 3D structures, and recovers these structures from 3D and 2D images via probabilistic inference, demonstrating for the first time the feasibility of learning to infer 3D representations of the world in a purely unsupervised manner. Expand
Synthesizing Programs for Images using Reinforced Adversarial Learning
SPIRAL is an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images, and a surprising finding is that using the discriminator's output as a reward signal is the key to allow the agent to make meaningful progress at matching the desired output rendering. Expand