Search Results for author: Alexis Joly

Found 13 papers, 3 papers with code

AI-based Mapping of the Conservation Status of Orchid Assemblages at Global Scale

no code implementations9 Jan 2024 Joaquim Estopinan, Maximilien Servajean, Pierre Bonnet, Alexis Joly, François Munoz

In Sumatra, we found good correspondence of protected areas with our indicators, but supplementing current IUCN assessments with status predictions results in alarming levels of species threat across the island.

The GeoLifeCLEF 2023 Dataset to evaluate plant species distribution models at high spatial resolution across Europe

no code implementations7 Aug 2023 Christophe Botella, Benjamin Deneu, Diego Marcos, Maximilien Servajean, Joaquim Estopinan, Théo Larcher, César Leblanc, Pierre Bonnet, Alexis Joly

We designed a European scale dataset covering around ten thousand plant species to calibrate and evaluate SDM predictions of species composition in space and time at high spatial resolution (~ten meters), and their spatial transferability.

A two-head loss function for deep Average-K classification

no code implementations31 Mar 2023 Camille Garcin, Maximilien Servajean, Alexis Joly, Joseph Salmon

Average-K classification is an alternative to top-K classification in which the number of labels returned varies with the ambiguity of the input image but must average to K over all the samples.

Classification Multi-Label Classification +1

Identify ambiguous tasks combining crowdsourced labels by weighting Areas Under the Margin

no code implementations30 Sep 2022 Tanguy Lefort, Benjamin Charlier, Alexis Joly, Joseph Salmon

We adapt the AUM to identify ambiguous tasks in crowdsourced learning scenarios, introducing the Weighted Areas Under the Margin (WAUM).

Image Classification

How does the degree of novelty impacts semi-supervised representation learning for novel class retrieval?

no code implementations17 Aug 2022 Quentin Leroy, Olivier Buisson, Alexis Joly

We hypothesize that incorporating unlabelled images of novel classes in the training set in a semi-supervised fashion would be beneficial for the efficient retrieval of novel-class images compared to a vanilla supervised representation.

Representation Learning Retrieval

Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification

1 code implementation4 Feb 2022 Camille Garcin, Maximilien Servajean, Alexis Joly, Joseph Salmon

In modern classification tasks, the number of labels is getting larger and larger, as is the size of the datasets encountered in practice.

imbalanced classification

Classification Under Ambiguity: When Is Average-K Better Than Top-K?

no code implementations16 Dec 2021 Titouan Lorieul, Alexis Joly, Dennis Shasha

This paper formally characterizes the ambiguity profile when average-$K$ classification can achieve a lower error rate than a fixed top-$K$ classification.


Hyperspherical embedding for novel class classification

no code implementations5 Feb 2021 Rafael S. Pereira, Alexis Joly, Patrick Valduriez, Fabio Porto

However, this traditional approach is not useful for identifying classes unseen on the training set, known as the open set problem.

Classification Few-Shot Learning +3

The GeoLifeCLEF 2020 Dataset

1 code implementation8 Apr 2020 Elijah Cole, Benjamin Deneu, Titouan Lorieul, Maximilien Servajean, Christophe Botella, Dan Morris, Nebojsa Jojic, Pierre Bonnet, Alexis Joly

Understanding the geographic distribution of species is a key concern in conservation.

Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory

no code implementations27 Nov 2019 Julien Herrmann, Olivier Beaumont, Lionel Eyraud-Dubois, Julien Hermann, Alexis Joly, Alena Shilova

This paper introduces a new activation checkpointing method which allows to significantly decrease memory usage when training Deep Neural Networks with the back-propagation algorithm.

Evaluation of Deep Species Distribution Models using Environment and Co-occurrences

no code implementations19 Sep 2019 Benjamin Deneu, Maximilien Servajean, Christophe Botella, Alexis Joly

This paper presents an evaluation of several approaches of plants species distribution modeling based on spatial, environmental and co-occurrences data using machine learning methods.

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