DECoVaC: Design of Experiments with Controlled Variability Components

no code implementations • 21 Sep 2019 • Thomas Boquet, Laure Delisle, Denis Kochetkov, Nathan Schucher, Parmida Atighehchian, Boris Oreshkin, Julien Cornebise

Reproducible research in Machine Learning has seen a salutary abundance of progress lately: workflows, transparency, and statistical analysis of validation and test performance.

BIG-bench Machine Learning Experimental Design

Multi-Class Few Shot Learning Task and Controllable Environment

no code implementations • 24 Mar 2019 • Dmitriy Serdyuk, Negar Rostamzadeh, Pedro Oliveira Pinheiro, Boris Oreshkin, Yoshua Bengio

In this paper, we address the task of classifying multiple objects by seeing only a few samples from each category.

Classification Few-Shot Learning

Adaptive Masked Weight Imprinting for Few-Shot Segmentation

no code implementations • ICLR Workshop LLD 2019 • Mennatullah Siam, Boris Oreshkin

Deep learning has mainly thrived by training on large-scale datasets.

Continual Learning Semantic Segmentation

Adaptive Masked Proxies for Few-Shot Segmentation

1 code implementation • 19 Feb 2019 • Mennatullah Siam, Boris Oreshkin, Martin Jagersand

Our method is evaluated on PASCAL-$5^i$ dataset and outperforms the state-of-the-art in the few-shot semantic segmentation.

Continual Learning Few-Shot Semantic Segmentation +4

Uncertainty in Multitask Transfer Learning

no code implementations • ICLR 2019 • Alexandre Lacoste, Boris Oreshkin, Wonchang Chung, Thomas Boquet, Negar Rostamzadeh, David Krueger

The result is a rich and meaningful prior capable of few-shot learning on new tasks.

Few-Shot Learning Transfer Learning

Deep Prior

no code implementations • 13 Dec 2017 • Alexandre Lacoste, Thomas Boquet, Negar Rostamzadeh, Boris Oreshkin, Wonchang Chung, David Krueger

The recent literature on deep learning offers new tools to learn a rich probability distribution over high dimensional data such as images or sounds.