Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics

1 code implementation • 10 Jun 2024 • Ankit Vani, Frederick Tung, Gabriel L. Oliveira, Hossein Sharifi-Noghabi

We propose that perturbations in SAM perform perturbed forgetting, where they discard undesirable model biases to exhibit learning signals that generalize better.

Domain Generalization via Semi-supervised Meta Learning

1 code implementation • 26 Sep 2020 • Hossein Sharifi-Noghabi, Hossein Asghari, Nazanin Mehrasa, Martin Ester

To learn a domain-invariant representation, it also utilizes a novel alignment loss to ensure that the distance between pairs of class centroids, computed after adding the unlabeled samples, is preserved across different domains.

Domain Generalization Meta-Learning

Adversarial Inductive Transfer Learning with input and output space adaptation

no code implementations • 25 Sep 2019 • Hossein Sharifi-Noghabi, Shuman Peng, Olga Zolotareva, Colin C. Collins, Martin Ester

To the best of our knowledge, AITL is the first adversarial inductive transfer learning method to address both input and output discrepancies.

Domain Adaptation Multi-Task Learning