From the 1 of 5 linked papers with an AI index.
5 papers
Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
Aristotelis Ballas, Christos Diou
The paper shows that both loss‑landscape flatness and gradient alignment are essential for multi‑distribution learning and introduces SAGE, a method that jointly optimizes these pr…
Gradient-Guided Annealing for Domain Generalization
Aristotelis Ballas, Christos Diou
Domain Generalization (DG) research has gained considerable traction as of late, since the ability to generalize to unseen data distributions is a requirement that eludes even stat…
Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning
Aristotelis Ballas, Vasileios Papapanagiotou, Christos Diou
Despite recent advancements in deep learning, its application in real-world medical settings, such as phonocardiogram (PCG) classification, remains limited. A significant barrier i…
CycleMix: Mixing Source Domains for Domain Generalization in Style-Dependent Data
Aristotelis Ballas, Christos Diou
As deep learning-based systems have become an integral part of everyday life, limitations in their generalization ability have begun to emerge. Machine learning algorithms typicall…
Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
Aristotelis Ballas, Christos Diou
During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite t…