17 citations · 72 across the 26 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020★ 14 cited
Leveraging Class Hierarchies with Metric-Guided Prototype Learning
Vivien Sainte Fare Garnot, Loic Landrieu
In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under t…
cs.LG2019★ 1 cited
Supervized Segmentation with Graph-Structured Deep Metric Learning
Loic Landrieu, Mohamed Boussaha
We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured b…