Search Results for author: Boris N. Oreshkin

Found 15 papers, 6 papers with code

Neural forecasting at scale

no code implementations20 Sep 2021 Philippe Chatigny, Shengrui Wang, Jean-Marc Patenaude, Boris N. Oreshkin

We study the problem of efficiently scaling ensemble-based deep neural networks for time series (TS) forecasting on a large set of time series.

Time Series

ProtoRes: Proto-Residual Architecture for Deep Modeling of Human Pose

no code implementations3 Jun 2021 Boris N. Oreshkin, Florent Bocquelet, Félix G. Harvey, Bay Raitt, Dominic Laflamme

Our work focuses on the development of a learnable neural representation of human pose for advanced AI assisted animation tooling.

Motion Capture Unity

Adaptive filters for the moving target indicator system

no code implementations31 Dec 2020 Boris N. Oreshkin

Regularization, also known in radar literature as sample covariance loading, can be used to combat both ill conditioning of the original problem and contamination of the empirical covariance by the desired signal for the adaptive algorithms based on sample covariance matrix inversion.

Optimization of loading factor preventing target cancellation

no code implementations9 Oct 2020 Boris N. Oreshkin, Peter A. Bakulev

Adaptive algorithms based on sample matrix inversion belong to an important class of algorithms used in radar target detection to overcome prior uncertainty of interference covariance.

Uncertainty driven probabilistic voxel selection for image registration

no code implementations2 Oct 2020 Boris N. Oreshkin, Tal Arbel

This paper presents a novel probabilistic voxel selection strategy for medical image registration in time-sensitive contexts, where the goal is aggressive voxel sampling (e. g. using less than 1% of the total number) while maintaining registration accuracy and low failure rate.

Image Registration Medical Image Registration

N-BEATS neural network for mid-term electricity load forecasting

1 code implementation24 Sep 2020 Boris N. Oreshkin, Grzegorz Dudek, Paweł Pełka, Ekaterina Turkina

We show that our proposed deep neural network modeling approach based on the deep neural architecture is effective at solving the mid-term electricity load forecasting problem.

Decision Making Load Forecasting +1

FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting

1 code implementation30 Jul 2020 Boris N. Oreshkin, Arezou Amini, Lucy Coyle, Mark J. Coates

Forecasting of multivariate time-series is an important problem that has applications in traffic management, cellular network configuration, and quantitative finance.

Time Series Time Series Forecasting

Meta-learning framework with applications to zero-shot time-series forecasting

2 code implementations7 Feb 2020 Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio

Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets?

Meta-Learning Time Series +1

Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings

no code implementations26 Jan 2020 Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand

Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels.

Few-Shot Learning One-shot visual object segmentation +3

One-Shot Weakly Supervised Video Object Segmentation

no code implementations18 Dec 2019 Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand

Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks.

Semantic Segmentation Video Object Segmentation +2

Adaptive Cross-Modal Few-Shot Learning

1 code implementation NeurIPS 2019 Chen Xing, Negar Rostamzadeh, Boris N. Oreshkin, Pedro O. Pinheiro

Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested.

Few-Shot Image Classification General Classification

TADAM: Task dependent adaptive metric for improved few-shot learning

3 code implementations NeurIPS 2018 Boris N. Oreshkin, Pau Rodriguez, Alexandre Lacoste

We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space.

Few-Shot Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.