most citedOptimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training

Roberto Sprengel Minozzo Tomchak, Oge Marques, Lucas Garcia Pedroso +2

The Triplet Margin Ranking Loss is one of the most widely used loss functions in Siamese Networks for solving Distance Metric Learning (DML) problems. This loss function depends on…