78 citations · 341 across the 20 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2022★ 1 cited
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification
Camille Garcin, Maximilien Servajean, Alexis Joly +1
In modern classification tasks, the number of labels is getting larger and larger, as is the size of the datasets encountered in practice. As the number of classes increases, class…
stat.ML2021
Classification Under Ambiguity: When Is Average-K Better Than Top-K?
Titouan Lorieul, Alexis Joly, Dennis Shasha
When many labels are possible, choosing a single one can lead to low precision. A common alternative, referred to as top- classification, is to choose some number (commonly…