Alert button
Picture for Sylvestre-Alvise Rebuffi

Sylvestre-Alvise Rebuffi

Alert button

Generative models improve fairness of medical classifiers under distribution shifts

Apr 18, 2023
Ira Ktena, Olivia Wiles, Isabela Albuquerque, Sylvestre-Alvise Rebuffi, Ryutaro Tanno, Abhijit Guha Roy, Shekoofeh Azizi, Danielle Belgrave, Pushmeet Kohli, Alan Karthikesalingam, Taylan Cemgil, Sven Gowal

Figure 1 for Generative models improve fairness of medical classifiers under distribution shifts
Figure 2 for Generative models improve fairness of medical classifiers under distribution shifts
Figure 3 for Generative models improve fairness of medical classifiers under distribution shifts
Figure 4 for Generative models improve fairness of medical classifiers under distribution shifts
Viaarxiv icon

Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts

Feb 20, 2023
Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer, Sven Gowal

Figure 1 for Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Figure 2 for Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Figure 3 for Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Figure 4 for Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Viaarxiv icon

NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

Nov 15, 2022
Jorg Bornschein, Alexandre Galashov, Ross Hemsley, Amal Rannen-Triki, Yutian Chen, Arslan Chaudhry, Xu Owen He, Arthur Douillard, Massimo Caccia, Qixuang Feng, Jiajun Shen, Sylvestre-Alvise Rebuffi, Kitty Stacpoole, Diego de las Casas, Will Hawkins, Angeliki Lazaridou, Yee Whye Teh, Andrei A. Rusu, Razvan Pascanu, Marc'Aurelio Ranzato

Figure 1 for NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Figure 2 for NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Figure 3 for NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Figure 4 for NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
Viaarxiv icon

Revisiting adapters with adversarial training

Oct 10, 2022
Sylvestre-Alvise Rebuffi, Francesco Croce, Sven Gowal

Figure 1 for Revisiting adapters with adversarial training
Figure 2 for Revisiting adapters with adversarial training
Figure 3 for Revisiting adapters with adversarial training
Figure 4 for Revisiting adapters with adversarial training
Viaarxiv icon

Data Augmentation Can Improve Robustness

Nov 09, 2021
Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

Figure 1 for Data Augmentation Can Improve Robustness
Figure 2 for Data Augmentation Can Improve Robustness
Figure 3 for Data Augmentation Can Improve Robustness
Figure 4 for Data Augmentation Can Improve Robustness
Viaarxiv icon

Improving Robustness using Generated Data

Oct 18, 2021
Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy Mann

Figure 1 for Improving Robustness using Generated Data
Figure 2 for Improving Robustness using Generated Data
Figure 3 for Improving Robustness using Generated Data
Figure 4 for Improving Robustness using Generated Data
Viaarxiv icon

AutoNovel: Automatically Discovering and Learning Novel Visual Categories

Jun 29, 2021
Kai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman

Figure 1 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Figure 2 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Figure 3 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Figure 4 for AutoNovel: Automatically Discovering and Learning Novel Visual Categories
Viaarxiv icon

Defending Against Image Corruptions Through Adversarial Augmentations

Apr 20, 2021
Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal

Figure 1 for Defending Against Image Corruptions Through Adversarial Augmentations
Figure 2 for Defending Against Image Corruptions Through Adversarial Augmentations
Figure 3 for Defending Against Image Corruptions Through Adversarial Augmentations
Figure 4 for Defending Against Image Corruptions Through Adversarial Augmentations
Viaarxiv icon

Fixing Data Augmentation to Improve Adversarial Robustness

Mar 02, 2021
Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

Figure 1 for Fixing Data Augmentation to Improve Adversarial Robustness
Figure 2 for Fixing Data Augmentation to Improve Adversarial Robustness
Figure 3 for Fixing Data Augmentation to Improve Adversarial Robustness
Figure 4 for Fixing Data Augmentation to Improve Adversarial Robustness
Viaarxiv icon