32 citations · 88 across the 23 of their papers we have counts for
7 papers · 1 filter
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…
Towards Fair Face Verification: An In-depth Analysis of Demographic Biases
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cl…
CNN Feature Map Augmentation for Single-Source Domain Generalization
Aristotelis Ballas, Christos Diou
In search of robust and generalizable machine learning models, Domain Generalization (DG) has gained significant traction during the past few years. The goal in DG is to produce mo…
CNNs with Multi-Level Attention for Domain Generalization
Aristotelis Ballas, Christos Diou
In the past decade, deep convolutional neural networks have achieved significant success in image classification and ranking and have therefore found numerous applications in multi…
FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many…
Multi-layer Representation Learning for Robust OOD Image Classification
Aristotelis Ballas, Christos Diou
Convolutional Neural Networks have become the norm in image classification. Nevertheless, their difficulty to maintain high accuracy across datasets has become apparent in the past…