6 code implementations • 2 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.
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.
9 code implementations • CVPR 2017 • Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, Christoph H. Lampert
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data.
Ranked #2 on Incremental Learning on ImageNet100 - 10 steps (# M Params metric)
1 code implementation • ICLR 2020 • Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman
In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use rank statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
1 code implementation • 29 Jun 2021 • Kai Han, Sylvestre-Alvise Rebuffi, Sébastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman
We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
Ranked #1 on Novel Class Discovery on SVHN
3 code implementations • CVPR 2018 • Sylvestre-Alvise Rebuffi, Hakan Bilen, Andrea Vedaldi
A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain.
2 code implementations • NeurIPS 2017 • Sylvestre-Alvise Rebuffi, Hakan Bilen, Andrea Vedaldi
There is a growing interest in learning data representations that work well for many different types of problems and data.
1 code implementation • 15 Nov 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
A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks.
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%).
1 code implementation • CVPR 2020 • Sylvestre-Alvise Rebuffi, Ruth Fong, Xu Ji, Andrea Vedaldi
Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample.
1 code implementation • 17 Jun 2020 • Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Kai Han, Andrea Vedaldi, Andrew Zisserman
We present LSD-C, a novel method to identify clusters in an unlabeled dataset.
1 code implementation • 21 May 2019 • Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Kai Han, Andrea Vedaldi, Andrew Zisserman
The first is a simple but effective one: we leverage the power of transfer learning among different tasks and self-supervision to initialize a good representation of the data without making use of any label.
no code implementations • 19 Oct 2019 • Sylvestre-Alvise Rebuffi, Ruth Fong, Xu Ji, Hakan Bilen, Andrea Vedaldi
In this paper, we are rather interested by the locations of an image that contribute to the model's training.
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.
no code implementations • 10 Oct 2022 • Sylvestre-Alvise Rebuffi, Francesco Croce, Sven Gowal
By co-training a neural network on clean and adversarial inputs, it is possible to improve classification accuracy on the clean, non-adversarial inputs.
no code implementations • CVPR 2023 • Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer, Sven Gowal
Adversarial training is widely used to make classifiers robust to a specific threat or adversary, such as $\ell_p$-norm bounded perturbations of a given $p$-norm.
no code implementations • 18 Apr 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
In our work, we show that learning realistic augmentations automatically from data is possible in a label-efficient manner using generative models.