activity
20192022
most citedLearning to run a power network challenge for training topology controllers

67 citations · 74 across the 5 of their papers we have counts for

collaborators

9 papers

cs.CV20222 cited

Giga-SSL: Self-Supervised Learning for Gigapixel Images

Tristan Lazard, Marvin Lerousseau, Etienne Decencière +1

Whole slide images (WSI) are microscopy images of stained tissue slides routinely prepared for diagnosis and treatment selection in medical practice. WSI are very large (gigapixel…

eess.IV2021

Weakly supervised pan-cancer segmentation tool

Marvin Lerousseau, Marion Classe, Enzo Battistella +8

The vast majority of semantic segmentation approaches rely on pixel-level annotations that are tedious and time consuming to obtain and suffer from significant inter and intra-expe…

cs.CV2021

SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification

Marvin Lerousseau, Maria Vakalopoulou, Eric Deutsch +1

Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracte…

cs.LG20211 cited

Design and implementation of an environment for Learning to Run a Power Network (L2RPN)

Marvin Lerousseau

This report summarizes work performed as part of an internship at INRIA, in partial requirement for the completion of a master degree in math and informatics. The goal of the inter…

q-bio.GN20213 cited

Cancer Gene Profiling through Unsupervised Discovery

Enzo Battistella, Maria Vakalopoulou, Roger Sun +9

Precision medicine is a paradigm shift in healthcare relying heavily on genomics data. However, the complexity of biological interactions, the large number of genes as well as the…

eess.IV20201 cited

Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution

Theophraste Henry, Alexandre Carre, Marvin Lerousseau +4

Brain tumor segmentation is a critical task for patient's disease management. In order to automate and standardize this task, we trained multiple U-net like neural networks, mainly…