Search Results for author: Shahine Bouabid

Found 8 papers, 7 papers with code

Domain Generalisation via Imprecise Learning

1 code implementation6 Apr 2024 Anurag Singh, Siu Lun Chau, Shahine Bouabid, Krikamol Muandet

Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e. g., optimising the average-case risk, worst-case risk, or interpolations thereof.

FaIRGP: A Bayesian Energy Balance Model for Surface Temperatures Emulation

1 code implementation14 Jul 2023 Shahine Bouabid, Dino Sejdinovic, Duncan Watson-Parris

The result is an emulator that \textit{(i)} enjoys the flexibility of statistical machine learning models and can learn from data, and \textit{(ii)} has a robust physical grounding with interpretable parameters that can be used to make inference about the climate system.

Uncertainty Quantification

Returning The Favour: When Regression Benefits From Probabilistic Causal Knowledge

1 code implementation26 Jan 2023 Shahine Bouabid, Jake Fawkes, Dino Sejdinovic

A directed acyclic graph (DAG) provides valuable prior knowledge that is often discarded in regression tasks in machine learning.


AODisaggregation: toward global aerosol vertical profiles

1 code implementation6 May 2022 Shahine Bouabid, Duncan Watson-Parris, Sofija Stefanović, Athanasios Nenes, Dino Sejdinovic

In this work, we develop a framework for the vertical disaggregation of AOD into extinction profiles, i. e. the measure of light extinction throughout an atmospheric column, using readily available vertically resolved meteorological predictors such as temperature, pressure or relative humidity.


Deconditional Downscaling with Gaussian Processes

1 code implementation NeurIPS 2021 Siu Lun Chau, Shahine Bouabid, Dino Sejdinovic

Yet, when LR samples are modeled as aggregate conditional means of HR samples with respect to a mediating variable that is globally observed, the recovery of the underlying fine-grained field can be framed as taking an "inverse" of the conditional expectation, namely a deconditioning problem.

Gaussian Processes

Predicting Landsat Reflectance with Deep Generative Fusion

1 code implementation9 Nov 2020 Shahine Bouabid, Maxim Chernetskiy, Maxime Rischard, Jevgenij Gamper

Public satellite missions are commonly bound to a trade-off between spatial and temporal resolution as no single sensor provides fine-grained acquisitions with frequent coverage.

Humanitarian Time Series +1

Mixup Regularization for Region Proposal based Object Detectors

no code implementations4 Mar 2020 Shahine Bouabid, Vincent Delaitre

Mixup - a neural network regularization technique based on linear interpolation of labeled sample pairs - has stood out by its capacity to improve model's robustness and generalizability through a surprisingly simple formalism.

Object object-detection +2

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