Christos Koutlis
YOU?
Author Swipe
View article: Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks
Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks Open
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 existing face image datasets often suffer from notable bias…
View article: VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation
VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation Open
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 intensified, progress continues to be hindered by fragmente…
View article: Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?
Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters? Open
The rapid advancement of generative technologies presents both unprecedented creative opportunities and significant challenges, particularly in maintaining social trust and ensuring the integrity of digital information. Following these con…
View article: Composite Data Augmentations for Synthetic Image Detection Against Real-World Perturbations
Composite Data Augmentations for Synthetic Image Detection Against Real-World Perturbations Open
The advent of accessible Generative AI tools enables anyone to create and spread synthetic images on social media, often with the intention to mislead, thus posing a significant threat to online information integrity. Most existing Synthet…
View article: Latent Multimodal Reconstruction for Misinformation Detection
Latent Multimodal Reconstruction for Misinformation Detection Open
Multimodal misinformation, such as miscaptioned images, where captions misrepresent an image's origin, context, or meaning, poses a growing challenge in the digital age. To support fact-checkers, researchers have focused on developing data…
View article: TextureCrop: Enhancing Synthetic Image Detection Through Texture-Based Cropping
TextureCrop: Enhancing Synthetic Image Detection Through Texture-Based Cropping Open
Generative AI technologies produce increasingly realistic imagery, which, despite its potential for creative applications, can also be misused to produce misleading and harmful content. This renders Synthetic Image Detection (SID) methods …
View article: Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks
Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks Open
View article: MAVias: Mitigate any Visual Bias
MAVias: Mitigate any Visual Bias Open
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 set of predefined biases, limiting their applicability in vis…
View article: DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization
DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization Open
Deepfake technology has rapidly advanced and poses significant threats to information integrity and trust in online multimedia. While significant progress has been made in detecting deepfakes, the simultaneous manipulation of audio and vis…
View article: FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations
FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations Open
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 recent research efforts focus on training fair models usin…
View article: A CLIP-based siamese approach for meme classification
A CLIP-based siamese approach for meme classification Open
Memes are an increasingly prevalent element of online discourse in social networks, especially among young audiences. They carry ideas and messages that range from humorous to hateful, and are widely consumed. Their potentially high impact…
View article: Zero-Shot Content-Based Crossmodal Recommendation System
Zero-Shot Content-Based Crossmodal Recommendation System Open
View article: PolyMeme: Fine-Grained Internet Meme Sensing
PolyMeme: Fine-Grained Internet Meme Sensing Open
Internet memes are a special type of digital content that is shared through social media. They have recently emerged as a popular new format of media communication. They are often multimodal, combining text with images and aim to express h…
View article: BAdd: Bias Mitigation through Bias Addition
BAdd: Bias Mitigation through Bias Addition Open
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, they fail in complex real-world scenarios. In particular, e…
View article: TextureCrop: Enhancing Synthetic Image Detection through Texture-based Cropping
TextureCrop: Enhancing Synthetic Image Detection through Texture-based Cropping Open
Generative AI technologies produce increasingly realistic imagery, which, despite its potential for creative applications, can also be misused to produce misleading and harmful content. This renders Synthetic Image Detection (SID) methods …
View article: Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection?
Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection? Open
Out-of-context (OOC) misinformation poses a significant challenge in multimodal fact-checking, where images are paired with texts that misrepresent their original context to support false narratives. Recent research in evidence-based OOC d…
View article: FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations
FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations Open
EXplainable Artificial Intelligence (XAI) approaches are widely applied for\nidentifying fairness issues in Artificial Intelligence (AI) systems. However,\nin the context of facial analysis, existing XAI approaches, such as pixel\nattribut…
View article: SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes
SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes Open
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 significant challenges. Many current face image datasets pri…
View article: FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems
FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems Open
View article: Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection
Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection Open
The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information. State-o…
View article: VERITE: a Robust benchmark for multimodal misinformation detection accounting for unimodal bias
VERITE: a Robust benchmark for multimodal misinformation detection accounting for unimodal bias Open
Multimedia content has become ubiquitous on social media platforms, leading to the rise of multimodal misinformation (MM) and the urgent need for effective strategies to detect and prevent its spread. In recent years, the challenge of mult…
View article: VERITE Benchmark
VERITE Benchmark Open
VERITE is a benchmark dataset designed for evaluating multimodal misinformation detection models. The dataset consists of real-world instances of misinformation collected from Snopes and Reuters and addresses unimodal bias by excluding asy…
View article: VERITE Benchmark
VERITE Benchmark Open
VERITE is a benchmark dataset designed for evaluating multimodal misinformation detection models. The dataset consists of real-world instances of misinformation collected from Snopes and Reuters and addresses unimodal bias by excluding asy…
View article: FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data
FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data Open
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 be covered in more detail. This paper offers an overview of…
View article: FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data Open
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 be covered in more detail. This paper offers an overview of…
View article: RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection
RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection Open
Online misinformation is often multimodal in nature, i.e., it is caused by misleading associations between texts and accompanying images. To support the fact-checking process, researchers have been recently developing automatic multimodal …
View article: FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning
FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning Open
The generalisation capacity of Multi-Task Learning (MTL) suffers when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients. This is known as negative transfer and leads to a drop in MTL accu…
View article: PolyMeme
PolyMeme Open
Internet Memes have emerged as a dominant new form of mass media and communication and they often consist of images that combine text with image and aim to express humor, irony, sarcasm, or sometimes convey hatred and misinformation. By re…
View article: PolyMeme
PolyMeme Open
Internet Memes have emerged as a dominant new form of mass media and communication and they often consist of images that combine text with image and aim to express humor, irony, sarcasm, or sometimes convey hatred and misinformation. By re…
View article: InDistill: Transferring Knowledge From Pruned Intermediate Layers
InDistill: Transferring Knowledge From Pruned Intermediate Layers Open
In this paper we introduce InDistill, a model compression approach that combines knowledge distillation and channel pruning in a unified framework for the transfer of the critical information flow paths from a heavyweight teacher to a ligh…