Research Scientist @ DeepMind
Email: oawiles AT deepmind.com
Email: oawiles AT google.com
Olivia Wiles
I work as a Senior Researcher at DeepMind, focussing on robustness of various forms: robustness to distribution shift and robustness to adversarial examples.
I was a DPhil student at the University of Oxford in the visual geometry group (VGG) supervised by Professor Andrew Zisserman.
Before that, I studied computer science at the University of Cambridge.
I also spent a wonderful summer working with Georgia Gkioxari, Justin Johnson, and Richard Szeliski at Facebook AI Research (FAIR).
-
Differentially Private Diffusion Models Generate Useful Synthetic Images
Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L Smith, Olivia Wiles, Borja Balle
arXiv, 2023
pdf
-
Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning
Olivia Wiles*, Isabela Albuquerque, Sven Gowal*
NeurIPS ML Safety Workshop, 2022 (Best Paper)
pdf
-
Compressed Vision for Efficient Video Understanding
Olivia Wiles, Joao Carreira, Iain Barr, Andrew Zisserman, Mateusz Malinowski
In Asian Conference on Computer Vision (ACCV), 2022
page
pdf
-
A Fine-Grained Analysis on Distribution Shift
Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre-Alvise Rebuffi, Ira Ktena, Krishnamurthy (DJ) Dvijotham, Taylan Cemgil
In International Conference on Learning Representations (ICLR), 2022 (oral)
pdf
code
-
Defending Against Image Corruption through Adversarial Augmentations
Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal
In International Conference on Learning Representations (ICLR), 2022
pdf
-
Improving Robustness using Generated Data
Sven Gowal*, Sylvestre-Alvise Rebuffi*, Olivia Wiles, Florian Stimberg, Dan A Calian, Timothy Mann
In Neural Information Processing Systems (NeurIPS), 2021
pdf
-
Data Augmentation Can Improve Robustness
Sylvestre-Alvise Rebuffi*, Sven Gowal*, Dan A Calian, Florian Stimberg, Olivia Wiles, Timothy Mann
In Neural Information Processing Systems (NeurIPS), 2021
pdf
-
-
-
-
-
-
X2face: A Network for Controlling Face Generation using Images, Audio, and Pose Codes
Olivia Wiles*, A Sophia Koepke*, Andrew Zisserman
In European Conference on Computer Vision (ECCV), 2018
page
pdf
-
Learning to Predict 3D Surfaces of Sculptures from Single and Multiple Views
Olivia Wiles, Andrew Zisserman
International Journal of Computer Vision (IJCV), 2019
pdf
-
SilNet: Single and Multi-view Reconstruction by Learning from Silhouettes
Olivia Wiles, Andrew Zisserman
In British Machine Vision Conference (BMVC), 2017 (Best Poster)
page
pdf
-
* denotes equal contribution
SELECTED WORKSHOP PUBLICATIONS
-
-
Self-supervised Learning of Class Embeddings from Video
Olivia Wiles, A Sophia Koepke, Andrew Zisserman
In International Conference on Computer Vision Workshops (ICCVW), 2019
pdf
-
3D Surface Reconstruction by Pointillism
Olivia Wiles, Andrew Zisserman
In European Conference on Computer Vision Workshops (ECCVW), 2018 (oral)
slides
pdf
Served as a PC for:
· Conferences: BMVC
Served as an AC for:
· Conferences: CVPR, ICCV, BMVC
Reviewed for:
· Conferences: ECCV, BMVC, CVPR, NeurIPS, ICCV, SIGGRAPH
· Journals: PAMI, CVIU
· Outstanding Reviewer: ICCV (2020), ICCV (2021)
