Jeffrey De Fauw — accepted AI-conference papers

2020

Self-Supervised MultiModal Versatile Networks

Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelović, Jason Ramapuram, Jeffrey De Fauw +3

NeurIPS 2020poster

Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the notion of a multimodal versatile network -- a network that…

Cited by 446 Source ↗PDF ↗code ↗Scholar ↗

2018

A Probabilistic U-Net for Segmentation of Ambiguous Images

Simon Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R. Ledsam, Klaus Maier-Hein +3

NeurIPS 2018spotlight

Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a set of diverse but plausible segmentations. We consider the t…

Cited by 705 Source ↗PDF ↗code ↗Scholar ↗

2016

Exploiting Cyclic Symmetry in Convolutional Neural Networks

Sander Dieleman, Jeffrey De Fauw, Koray Kavukcuoglu

ICML 2016poster

Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equivariance properties from the data. Encoding these properties into the network architecture, as we are…

Cited by 458 Source ↗PDF ↗Scholar ↗