7 citations · 8 across the 2 of their papers we have counts for
3 papers
cs.CV2022★ 7 cited
Efficient Multiscale Object-based Superpixel Framework
Felipe Belém, Benjamin Perret, Jean Cousty +2
Superpixel segmentation can be used as an intermediary step in many applications, often to improve object delineation and reduce computer workload. However, classical methods do no…
cs.LG2021★ 1 cited
Component Tree Loss Function: Definition and Optimization
Benjamin Perret, Jean Cousty
In this article, we propose a method to design loss functions based on component trees which can be optimized by gradient descent algorithms and which are therefore usable in conju…
cs.LG2019
Ultrametric Fitting by Gradient Descent
Giovanni Chierchia, Benjamin Perret
We study the problem of fitting an ultrametric distance to a dissimilarity graph in the context of hierarchical cluster analysis. Standard hierarchical clustering methods are speci…