no code implementations • 25 Apr 2024 • Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kajić, Su Wang, Emanuele Bugliarello, Yasumasa Onoe, Chris Knutsen, Cyrus Rashtchian, Jordi Pont-Tuset, Aida Nematzadeh
Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated.
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.
no code implementations • 18 Aug 2022 • Olivia Wiles, Isabela Albuquerque, Sven Gowal
Misclassified inputs are clustered and a captioning model is used to describe each cluster.
no code implementations • 1 Jan 2021 • Joao Monteiro, Isabela Albuquerque, Jahangir Alam, Tiago Falk
Recent metric learning approaches parametrize semantic similarity measures through the use of an encoder trained along with a similarity model, which operates over pairs of representations.
no code implementations • 30 Mar 2020 • Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar, Richard Socher
Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness.
Ranked #116 on Domain Generalization on PACS
1 code implementation • ICML 2020 • Joao Monteiro, Isabela Albuquerque, Jahangir Alam, R. Devon Hjelm, Tiago Falk
In this contribution, we augment the metric learning setting by introducing a parametric pseudo-distance, trained jointly with the encoder.
1 code implementation • 13 Nov 2019 • Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort
The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains.
2 code implementations • 3 Nov 2019 • Isabela Albuquerque, João Monteiro, Mohammad Darvishi, Tiago H. Falk, Ioannis Mitliagkas
In this work, we tackle such problem by focusing on domain generalization: a formalization where the data generating process at test time may yield samples from never-before-seen domains (distributions).
Ranked #61 on Domain Generalization on PACS
no code implementations • 20 Jun 2019 • Isabela Albuquerque, João Monteiro, Olivier Rosanne, Abhishek Tiwari, Jean-François Gagnon, Tiago H. Falk
Besides shedding light on the assumptions that hold for a particular dataset, the estimates of statistical shifts obtained with the proposed approach can be used for investigating other aspects of a machine learning pipeline, such as quantitatively assessing the effectiveness of domain adaptation strategies.
1 code implementation • ICLR 2019 • Isabela Albuquerque, João Monteiro, Thang Doan, Breandan Considine, Tiago Falk, Ioannis Mitliagkas
Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary.
1 code implementation • 23 Jan 2019 • Isabela Albuquerque, João Monteiro, Tiago H. Falk
Afterwards, a recurrent model is trained with the goal of providing a sequence of inputs to the previously trained frames generator, thus yielding scenes which look natural.
3 code implementations • 16 Jan 2019 • Yannick Roy, Hubert Banville, Isabela Albuquerque, Alexandre Gramfort, Tiago H. Falk, Jocelyn Faubert
To help the field progress, we provide a list of recommendations for future studies and we make our summary table of DL and EEG papers available and invite the community to contribute.
3 code implementations • 31 Jul 2018 • Thang Doan, Joao Monteiro, Isabela Albuquerque, Bogdan Mazoure, Audrey Durand, Joelle Pineau, R. Devon Hjelm
We argue that less expressive discriminators are smoother and have a general coarse grained view of the modes map, which enforces the generator to cover a wide portion of the data distribution support.
no code implementations • 21 Feb 2018 • João Monteiro, Isabela Albuquerque, Zahid Akhtar, Tiago H. Falk
Non-linear binary classifiers trained on top of our proposed features can achieve a high detection rate (>90%) in a set of white-box attacks and maintain such performance when tested against unseen attacks.