2 citations · 7 across the 13 of their papers we have counts for
15 papers
Scaling Vision-Language Models Is Not Enough to Mitigate Bias
Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present…
Face Age Verification Vulnerabilities Under Simple Appearance Manipulations
Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Online platforms increasingly rely on automated age estimation systems to enforce minimum-age policies. Focusing on vision-based models designed for this task, concerns arise regar…
Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks
Georgia Baltsou, Ioannis Sarridis, Christos Koutlis +1
Face verification is a significant component of identity authentication in various applications including online banking and secure access to personal devices. The majority of the…
VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
Bias in computer vision models remains a significant challenge, often resulting in unfair, unreliable, and non-generalizable AI systems. Although research into bias mitigation has…
FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
EXplainable Artificial Intelligence (XAI) approaches are widely applied for identifying fairness issues in Artificial Intelligence (AI) systems. However, in the context of facial a…
MAVias: Mitigate any Visual Bias
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
Mitigating biases in computer vision models is an essential step towards the trustworthiness of artificial intelligence models. Existing bias mitigation methods focus on a small se…
BAdd: Bias Mitigation through Bias Addition
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations,…
SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes
Georgia Baltsou, Ioannis Sarridis, Christos Koutlis +1
AI systems rely on extensive training on large datasets to address various tasks. However, image-based systems, particularly those used for demographic attribute prediction, face s…
FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez +44
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must…
Mitigating Viewer Impact from Disturbing Imagery using AI Filters: A User-Study
Ioannis Sarridis, Jochen Spangenberg, Olga Papadopoulou +1
Exposure to disturbing imagery can significantly impact individuals, especially professionals who encounter such content as part of their work. This paper presents a user study, in…
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…
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…
Leveraging Large-scale Multimedia Datasets to Refine Content Moderation Models
Ioannis Sarridis, Christos Koutlis, Olga Papadopoulou +1
The sheer volume of online user-generated content has rendered content moderation technologies essential in order to protect digital platform audiences from content that may cause…
InDistill: Information flow-preserving knowledge distillation for model compression
Ioannis Sarridis, Christos Koutlis, Giorgos Kordopatis-Zilos +2
In this paper, we introduce InDistill, a method that serves as a warmup stage for enhancing Knowledge Distillation (KD) effectiveness. InDistill focuses on transferring critical in…
Block Randomized Optimization for Adaptive Hypergraph Learning
Georgios Karantaidis, Ioannis Sarridis, Constantine Kotropoulos
The high-order relations between the content in social media sharing platforms are frequently modeled by a hypergraph. Either hypergraph Laplacian matrix or the adjacency matrix is…