5 papers · 1 filter
LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups
Masih Aminbeidokhti, Subhankar Roy, Eric Granger +2
Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely underrepresented. While recent work shows…
High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
Masih Aminbeidokhti, Heitor Rapela Medeiros, Srikanth Muralidharan +2
Ensembling fine-tuned models initialized from powerful pre-trained weights is a common strategy to improve robustness under distribution shifts, but it comes with substantial compu…
Revisiting Mixout: An Overlooked Path to Robust Finetuning
Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger +1
Finetuning vision foundation models often improves in-domain accuracy but comes at the cost of robustness under distribution shift. We revisit Mixout, a stochastic regularizer that…
Domain Generalization by Rejecting Extreme Augmentations
Masih Aminbeidokhti, Fidel A. Guerrero Peña, Heitor Rapela Medeiros +3
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. Howev…
Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation
Muhammad Haseeb Aslam, Clara Martinez, Marco Pedersoli +3
Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can su…