Search Results for author: Olivia Wiles

Found 18 papers, 5 papers with code

Differentially Private Diffusion Models Generate Useful Synthetic Images

no code implementations27 Feb 2023 Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L. Smith, Olivia Wiles, Borja Balle

By privately fine-tuning ImageNet pre-trained diffusion models with more than 80M parameters, we obtain SOTA results on CIFAR-10 and Camelyon17 in terms of both FID and the accuracy of downstream classifiers trained on synthetic data.

Image Generation Privacy Preserving

Compressed Vision for Efficient Video Understanding

no code implementations6 Oct 2022 Olivia Wiles, Joao Carreira, Iain Barr, Andrew Zisserman, Mateusz Malinowski

In this work, we propose a framework enabling research on hour-long videos with the same hardware that can now process second-long videos.

Video Compression Video Understanding

Data Augmentation Can Improve Robustness

1 code implementation NeurIPS 2021 Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training.

Data Augmentation

A Fine-Grained Analysis on Distribution Shift

no code implementations ICLR 2022 Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre Alvise-Rebuffi, Ira Ktena, Krishnamurthy Dvijotham, Taylan Cemgil

Despite this necessity, there has been little work in defining the underlying mechanisms that cause these shifts and evaluating the robustness of algorithms across multiple, different distribution shifts.

Improving Robustness using Generated Data

1 code implementation NeurIPS 2021 Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy Mann

Against $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our models achieve 66. 10% and 33. 49% robust accuracy on CIFAR-10 and CIFAR-100, respectively (improving upon the state-of-the-art by +8. 96% and +3. 29%).

Adversarial Robustness

Defending Against Image Corruptions Through Adversarial Augmentations

no code implementations ICLR 2022 Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal

Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog.

Image Classification

Fixing Data Augmentation to Improve Adversarial Robustness

6 code implementations2 Mar 2021 Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

In particular, against $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our model reaches 64. 20% robust accuracy without using any external data, beating most prior works that use external data.

Adversarial Robustness Data Augmentation

Co-Attention for Conditioned Image Matching

no code implementations CVPR 2021 Olivia Wiles, Sebastien Ehrhardt, Andrew Zisserman

We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material.

3D Reconstruction Camera Localization +2

SynSin: End-to-end View Synthesis from a Single Image

3 code implementations CVPR 2020 Olivia Wiles, Georgia Gkioxari, Richard Szeliski, Justin Johnson

Single image view synthesis allows for the generation of new views of a scene given a single input image.

Novel View Synthesis

Self-supervised learning of class embeddings from video

no code implementations28 Oct 2019 Olivia Wiles, A. Sophia Koepke, Andrew Zisserman

This work explores how to use self-supervised learning on videos to learn a class-specific image embedding that encodes pose and shape information.

Self-Supervised Learning

3D Surface Reconstruction by Pointillism

no code implementations6 Sep 2018 Olivia Wiles, Andrew Zisserman

Finally, we demonstrate that we can indeed obtain a depth map of a novel object from a single image for a variety of sculptures with varying shape/texture, and that the network generalises at test time to new domains (e. g. synthetic images).

Surface Reconstruction

X2Face: A network for controlling face generation using images, audio, and pose codes

no code implementations ECCV 2018 Olivia Wiles, A. Sophia Koepke, Andrew Zisserman

The objective of this paper is a neural network model that controls the pose and expression of a given face, using another face or modality (e. g. audio).

Talking Head Generation

Self-supervised learning of a facial attribute embedding from video

2 code implementations21 Aug 2018 Olivia Wiles, A. Sophia Koepke, Andrew Zisserman

We propose a self-supervised framework for learning facial attributes by simply watching videos of a human face speaking, laughing, and moving over time.

Attribute Self-Supervised Learning +1

X2Face: A network for controlling face generation by using images, audio, and pose codes

no code implementations27 Jul 2018 Olivia Wiles, A. Sophia Koepke, Andrew Zisserman

The objective of this paper is a neural network model that controls the pose and expression of a given face, using another face or modality (e. g. audio).

Face Generation

SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettes

no code implementations21 Nov 2017 Olivia Wiles, Andrew Zisserman

The objective of this paper is 3D shape understanding from single and multiple images.

Cannot find the paper you are looking for? You can Submit a new open access paper.