2 papers
cs.LG2026
Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validation
Lorenzo Brigato, Stavroula Mougiakakou
We introduce Tune without Validation (Twin), a simple and effective pipeline for tuning learning rate and weight decay of homogeneous classifiers without validation sets, eliminati…
cs.CV2024
A SAM based Tool for Semi-Automatic Food Annotation
Lubnaa Abdur Rahman, Ioannis Papathanail, Lorenzo Brigato +1
The advancement of artificial intelligence (AI) in food and nutrition research is hindered by a critical bottleneck: the lack of annotated food data. Despite the rise of highly eff…