Christos Koutlis

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

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 multimodal misinformation detection (MMD) has garnered significant attention by researchers and has mainly involved the creation of annotated, weakly annotated, or synthetically generated training datasets, along with the development of various deep learning MMD models. However, the problem of unimodal bias has been overlooked, where specific patterns and biases in MMD benchmarks can result in biased or unimodal models outperforming their multimodal counterparts on an inherently multimodal task; making it difficult to assess progress. In this study, we systematically investigate and identify the presence of unimodal bias in widely-used MMD benchmarks, namely VMU-Twitter and COSMOS. To address this issue, we introduce the "VERification of Image-TExt pairs" (VERITE) benchmark for MMD which incorporates real-world data, excludes "asymmetric multimodal misinformation" and utilizes "modality balancing". We conduct an extensive comparative study with a Transformer-based architecture that shows the ability of VERITE to effectively address unimodal bias, rendering it a robust evaluation framework for MMD. Furthermore, we introduce a new method -- termed Crossmodal HArd Synthetic MisAlignment (CHASMA) -- for generating realistic synthetic training data that preserve crossmodal relations between legitimate images and false human-written captions. By leveraging CHASMA in the training process, we observe consistent and notable improvements in predictive performance on VERITE; with a 9.2% increase in accuracy. We release our code at: https://github.com/stevejpapad/image-text-verification

Christos Koutlis, Manos Schinas, Symeon Papadopoulos

Hate speech is a societal problem that has significantly grown through the Internet. New forms of digital content such as image memes have given rise to spread of hate using multimodal means, being far more difficult to analyse and detect compared to the unimodal case. Accurate automatic processing, analysis and understanding of this kind of content will facilitate the endeavor of hindering hate speech proliferation through the digital world. To this end, we propose MemeFier, a deep learning-based architecture for fine-grained classification of Internet image memes, utilizing a dual-stage modality fusion module. The first fusion stage produces feature vectors containing modality alignment information that captures non-trivial connections between the text and image of a meme. The second fusion stage leverages the power of a Transformer encoder to learn inter-modality correlations at the token level and yield an informative representation. Additionally, we consider external knowledge as an additional input, and background image caption supervision as a regularizing component. Extensive experiments on three widely adopted benchmarks, i.e., Facebook Hateful Memes, Memotion7k and MultiOFF, indicate that our approach competes and in some cases surpasses state-of-the-art. Our code is available on https://github.com/ckoutlis/memefier.

Christos Koutlis, Manos Schinas, Symeon Papadopoulos

Image memes and specifically their widely-known variation image macros, is a special new media type that combines text with images and is used in social media to playfully or subtly express humour, irony, sarcasm and even hate. It is important to accurately retrieve image memes from social media to better capture the cultural and social aspects of online phenomena and detect potential issues (hate-speech, disinformation). Essentially, the background image of an image macro is a regular image easily recognized as such by humans but cumbersome for the machine to do so due to feature map similarity with the complete image macro. Hence, accumulating suitable feature maps in such cases can lead to deep understanding of the notion of image memes. To this end, we propose a methodology, called Visual Part Utilization, that utilizes the visual part of image memes as instances of the regular image class and the initial image memes as instances of the image meme class to force the model to concentrate on the critical parts that characterize an image meme. Additionally, we employ a trainable attention mechanism on top of a standard ViT architecture to enhance the model's ability to focus on these critical parts and make the predictions interpretable. Several training and test scenarios involving web-scraped regular images of controlled text presence are considered for evaluating the model in terms of robustness and accuracy. The findings indicate that light visual part utilization combined with sufficient text presence during training provides the best and most robust model, surpassing state of the art. Source code and dataset are available at https://github.com/mever-team/memetector.

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

For fashion outfits to be considered aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color. Previous works have defined visual compatibility as a binary classification task with items in a garment being considered as fully compatible or fully incompatible. However, this is not applicable to Outfit Maker applications where users create their own outfits and need to know which specific items may be incompatible with the rest of the outfit. To address this, we propose the Visual InCompatibility TransfORmer (VICTOR) that is optimized for two tasks: 1) overall compatibility as regression and 2) the detection of mismatching items and utilize fashion-specific contrastive language-image pre-training for fine tuning computer vision neural networks on fashion imagery. We build upon the Polyvore outfit benchmark to generate partially mismatching outfits, creating a new dataset termed Polyvore-MISFITs, that is used to train VICTOR. A series of ablation and comparative analyses show that the proposed architecture can compete and even surpass the current state-of-the-art on Polyvore datasets while reducing the instance-wise floating operations by 88%, striking a balance between high performance and efficiency. We release our code at https://github.com/stevejpapad/Visual-InCompatibility-Transformer

Ioannis Sarridis, Christos Koutlis, Giorgos Kordopatis-Zilos et al.

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 information flow paths from a heavyweight teacher to a lightweight student. This is achieved via a training scheme based on curriculum learning that considers the distillation difficulty of each layer and the critical learning periods when the information flow paths are established. This procedure can lead to a student model that is better prepared to learn from the teacher. To ensure the applicability of InDistill across a wide range of teacher-student pairs, we also incorporate a pruning operation when there is a discrepancy in the width of the teacher and student layers. This pruning operation reduces the width of the teacher's intermediate layers to match those of the student, allowing direct distillation without the need for an encoding stage. The proposed method is extensively evaluated using various pairs of teacher-student architectures on CIFAR-10, CIFAR-100, and ImageNet datasets demonstrating that preserving the information flow paths consistently increases the performance of the baseline KD approaches on both classification and retrieval settings. The code is available at https://github.com/gsarridis/InDistill.

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

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 methods that gather and analyze external information, evidence, related to the image-text pairs under examination. However, prior works assumed all external information collected from the web to be relevant. In this study, we introduce a "Relevant Evidence Detection" (RED) module to discern whether each piece of evidence is relevant, to support or refute the claim. Specifically, we develop the "Relevant Evidence Detection Directed Transformer" (RED-DOT) and explore multiple architectural variants (e.g., single or dual-stage) and mechanisms (e.g., "guided attention"). Extensive ablation and comparative experiments demonstrate that RED-DOT achieves significant improvements over the state-of-the-art (SotA) on the VERITE benchmark by up to 33.7%. Furthermore, our evidence re-ranking and element-wise modality fusion led to RED-DOT surpassing the SotA on NewsCLIPings+ by up to 3% without the need for numerous evidence or multiple backbone encoders. We release our code at: https://github.com/stevejpapad/relevant-evidence-detection

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

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 detection has seen a trend towards increasingly complex architectures, incorporating Transformers, foundation models, and large language models. In this study, we introduce a simple yet robust baseline, which assesses MUltimodal SimilaritiEs (MUSE), specifically the similarity between image-text pairs and external image and text evidence. Our results demonstrate that MUSE, when used with conventional classifiers like Decision Tree, Random Forest, and Multilayer Perceptron, can compete with and even surpass the state-of-the-art on the NewsCLIPpings and VERITE datasets. Furthermore, integrating MUSE in our proposed "Attentive Intermediate Transformer Representations" (AITR) significantly improved performance, by 3.3% and 7.5% on NewsCLIPpings and VERITE, respectively. Nevertheless, the success of MUSE, relying on surface-level patterns and shortcuts, without examining factuality and logical inconsistencies, raises critical questions about how we define the task, construct datasets, collect external evidence and overall, how we assess progress in the field. We release our code at: https://github.com/stevejpapad/outcontext-misinfo-progress

Despina Konstantinidou, Christos Koutlis, Symeon Papadopoulos

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 essential for identifying AI-generated content online. State-of-the-art SID methods typically resize or center-crop input images due to architectural or computational constraints, which hampers the detection of artifacts that appear in high-resolution images. To address this limitation, we propose TextureCrop, an image pre-processing component that can be plugged in any pre-trained SID model to improve its performance. By focusing on high-frequency image parts where generative artifacts are prevalent, TextureCrop enhances SID performance with manageable memory requirements. Experimental results demonstrate a consistent improvement in AUC across various detectors by 6.1% compared to center cropping and by 15% compared to resizing, across high-resolution images from the Forensynths, Synthbuster and TWIGMA datasets. Code available at https : //github.com/mever-team/texture-crop.

Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez et al.

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 the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first international challenge aiming to explore the use of synthetic data in face recognition to address existing limitations in the technology. Specifically, the FRCSyn Challenge targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. The results achieved in the FRCSyn Challenge, together with the proposed benchmark, contribute significantly to the application of synthetic data to improve face recognition technology.

Stefanos I. Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend detection in fashion is a challenging task due to the fast pace of change in the fashion industry. Moreover, forecasting the visual popularity of new garment designs is even more demanding due to lack of historical data. To this end, we propose MuQAR, a Multimodal Quasi-AutoRegressive deep learning architecture that combines two modules: (1) a multi-modal multi-layer perceptron processing categorical, visual and textual features of the product and (2) a quasi-autoregressive neural network modelling the "target" time series of the product's attributes along with the "exogenous" time series of all other attributes. We utilize computer vision, image classification and image captioning, for automatically extracting visual features and textual descriptions from the images of new products. Product design in fashion is initially expressed visually and these features represent the products' unique characteristics without interfering with the creative process of its designers by requiring additional inputs (e.g manually written texts). We employ the product's target attributes time series as a proxy of temporal popularity patterns, mitigating the lack of historical data, while exogenous time series help capture trends among interrelated attributes. We perform an extensive ablation analysis on two large scale image fashion datasets, Mallzee and SHIFT15m to assess the adequacy of MuQAR and also use the Amazon Reviews: Home and Kitchen dataset to assess generalisability to other domains. A comparative study on the VISUELLE dataset, shows that MuQAR is capable of competing and surpassing the domain's current state of the art by 4.65% and 4.8% in terms of WAPE and MAE respectively.

Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos et al.

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 using such data. However, most of them heavily rely on the availability of protected attribute labels in the dataset, which limits their applicability, while label-unaware approaches, i.e., approaches operating without such labels, exhibit considerably lower performance. To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual information between the features extracted by the model and a protected attribute, without the use of attribute labels. To do that, FLAC proposes a sampling strategy that highlights underrepresented samples in the dataset, and casts the problem of learning fair representations as a probability matching problem that leverages representations extracted by a bias-capturing classifier. It is theoretically shown that FLAC can indeed lead to fair representations, that are independent of the protected attributes. FLAC surpasses the current state-of-the-art on Biased-MNIST, CelebA, and UTKFace, by 29.1%, 18.1%, and 21.9%, respectively. Additionally, FLAC exhibits 2.2% increased accuracy on ImageNet-A and up to 4.2% increased accuracy on Corrupted-Cifar10. Finally, in most experiments, FLAC even outperforms the bias label-aware state-of-the-art methods.

Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos et al.

Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cloud-based solutions, have been found to exhibit significant biases related to race, age, and gender, a problem that requires in-depth exploration and solutions. This paper presents an in-depth analysis, with a particular emphasis on the intersectionality of these demographic factors. Intersectional bias refers to the performance discrepancies w.r.t. the different combinations of race, age, and gender groups, an area relatively unexplored in current literature. Furthermore, the reliance of most state-of-the-art approaches on accuracy as the principal evaluation metric often masks significant demographic disparities in performance. To counter this crucial limitation, we incorporate five additional metrics in our quantitative analysis, including disparate impact and mistreatment metrics, which are typically ignored by the relevant fairness-aware approaches. Results on the Racial Faces in-the-Wild (RFW) benchmark indicate pervasive biases in face recognition systems, extending beyond race, with different demographic factors yielding significantly disparate outcomes. In particular, Africans demonstrate an 11.25% lower True Positive Rate (TPR) compared to Caucasians, while only a 3.51% accuracy drop is observed. Even more concerning, the intersections of multiple protected groups, such as African females over 60 years old, demonstrate a +39.89% disparate mistreatment rate compared to the highest Caucasians rate. By shedding light on these biases and their implications, this paper aims to stimulate further research towards developing fairer, more equitable face recognition and verification systems.

Ioannis Sarridis, Christos Koutlis, Olga Papadopoulou et al.

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 anxiety, worry, or concern. Despite the efforts towards developing automated solutions to tackle this problem, creating accurate models remains challenging due to the lack of adequate task-specific training data. The fact that manually annotating such data is a highly demanding procedure that could severely affect the annotators' emotional well-being is directly related to the latter limitation. In this paper, we propose the CM-Refinery framework that leverages large-scale multimedia datasets to automatically extend initial training datasets with hard examples that can refine content moderation models, while significantly reducing the involvement of human annotators. We apply our method on two model adaptation strategies designed with respect to the different challenges observed while collecting data, i.e. lack of (i) task-specific negative data or (ii) both positive and negative data. Additionally, we introduce a diversity criterion applied to the data collection process that further enhances the generalization performance of the refined models. The proposed method is evaluated on the Not Safe for Work (NSFW) and disturbing content detection tasks on benchmark datasets achieving 1.32% and 1.94% accuracy improvements compared to the state of the art, respectively. Finally, it significantly reduces human involvement, as 92.54% of data are automatically annotated in case of disturbing content while no human intervention is required for the NSFW task.

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

With the expansion of social media and the increasing dissemination of multimedia content, the spread of misinformation has become a major concern. This necessitates effective strategies for multimodal misinformation detection (MMD) that detect whether the combination of an image and its accompanying text could mislead or misinform. Due to the data-intensive nature of deep neural networks and the labor-intensive process of manual annotation, researchers have been exploring various methods for automatically generating synthetic multimodal misinformation - which we refer to as Synthetic Misinformers - in order to train MMD models. However, limited evaluation on real-world misinformation and a lack of comparisons with other Synthetic Misinformers makes difficult to assess progress in the field. To address this, we perform a comparative study on existing and new Synthetic Misinformers that involves (1) out-of-context (OOC) image-caption pairs, (2) cross-modal named entity inconsistency (NEI) as well as (3) hybrid approaches and we evaluate them against real-world misinformation; using the COSMOS benchmark. The comparative study showed that our proposed CLIP-based Named Entity Swapping can lead to MMD models that surpass other OOC and NEI Misinformers in terms of multimodal accuracy and that hybrid approaches can lead to even higher detection accuracy. Nevertheless, after alleviating information leakage from the COSMOS evaluation protocol, low Sensitivity scores indicate that the task is significantly more challenging than previous studies suggested. Finally, our findings showed that NEI-based Synthetic Misinformers tend to suffer from a unimodal bias, where text-only MMDs can outperform multimodal ones.

Arjun Roy, Christos Koutlis, Symeon Papadopoulos et al.

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 accuracy compared to single-task learning (STL). Lately, there has been a growing focus on the fairness of MTL models, requiring the optimization of both accuracy and fairness for individual tasks. Analogously to negative transfer for accuracy, task-specific fairness considerations might adversely affect the fairness of other tasks when there is a conflict of fairness loss gradients between the jointly learned tasks - we refer to this as Bias Transfer. To address both negative- and bias-transfer in MTL, we propose a novel method called FairBranch, which branches the MTL model by assessing the similarity of learned parameters, thereby grouping related tasks to alleviate negative transfer. Moreover, it incorporates fairness loss gradient conflict correction between adjoining task-group branches to address bias transfer within these task groups. Our experiments on tabular and visual MTL problems show that FairBranch outperforms state-of-the-art MTLs on both fairness and accuracy.

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Anastasios Papazoglou-Chalikias et al.

Being able to forecast the popularity of new garment designs is very important in an industry as fast paced as fashion, both in terms of profitability and reducing the problem of unsold inventory. Here, we attempt to address this task in order to provide informative forecasts to fashion designers within a virtual reality designer application that will allow them to fine tune their creations based on current consumer preferences within an interactive and immersive environment. To achieve this we have to deal with the following central challenges: (1) the proposed method should not hinder the creative process and thus it has to rely only on the garment's visual characteristics, (2) the new garment lacks historical data from which to extrapolate their future popularity and (3) fashion trends in general are highly dynamical. To this end, we develop a computer vision pipeline fine tuned on fashion imagery in order to extract relevant visual features along with the category and attributes of the garment. We propose a hierarchical label sharing (HLS) pipeline for automatically capturing hierarchical relations among fashion categories and attributes. Moreover, we propose MuQAR, a Multimodal Quasi-AutoRegressive neural network that forecasts the popularity of new garments by combining their visual features and categorical features while an autoregressive neural network is modelling the popularity time series of the garment's category and attributes. Both the proposed HLS and MuQAR prove capable of surpassing the current state-of-the-art in key benchmark datasets, DeepFashion for image classification and VISUELLE for new garment sales forecasting.

Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos et al.

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, existing methods excel in controlled experiments involving benchmarks with single-attribute injected biases, but struggle with multi-attribute biases being present in well-established CV datasets. Here, we introduce BAdd, a simple yet effective method that allows for learning fair representations invariant to the attributes introducing bias by incorporating features representing these attributes into the backbone. BAdd is evaluated on seven benchmarks and exhibits competitive performance, surpassing state-of-the-art methods on both single- and multi-attribute benchmarks. Notably, BAdd achieves +27.5% and +5.5% absolute accuracy improvements on the challenging multi-attribute benchmarks, FB-Biased-MNIST and CelebA, respectively.

Christos Koutlis, Symeon Papadopoulos

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-of-the-art Synthetic Image Detection (SID) research has led to strong evidence on the advantages of feature extraction from foundation models. However, such extracted features mostly encapsulate high-level visual semantics instead of fine-grained details, which are more important for the SID task. On the contrary, shallow layers encode low-level visual information. In this work, we leverage the image representations extracted by intermediate Transformer blocks of CLIP's image-encoder via a lightweight network that maps them to a learnable forgery-aware vector space capable of generalizing exceptionally well. We also employ a trainable module to incorporate the importance of each Transformer block to the final prediction. Our method is compared against the state-of-the-art by evaluating it on 20 test datasets and exhibits an average +10.6% absolute performance improvement. Notably, the best performing models require just a single epoch for training (~8 minutes). Code available at https://github.com/mever-team/rine.

Christos Koutlis, Symeon Papadopoulos

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 visual modalities, sometimes at small parts or in subtle ways, presents highly challenging detection scenarios. To address these challenges, we present DiMoDif, an audio-visual deepfake detection framework that leverages the inter-modality differences in machine perception of speech, based on the assumption that in real samples -- in contrast to deepfakes -- visual and audio signals coincide in terms of information. DiMoDif leverages features from deep networks that specialize in visual and audio speech recognition to spot frame-level cross-modal incongruities, and in that way to temporally localize the deepfake forgery. To this end, we devise a hierarchical cross-modal fusion network, integrating adaptive temporal alignment modules and a learned discrepancy mapping layer to explicitly model the subtle differences between visual and audio representations. Then, the detection model is optimized through a composite loss function accounting for frame-level detections and fake intervals localization. DiMoDif outperforms the state-of-the-art on the Deepfake Detection task by 30.5 AUC on the highly challenging AV-Deepfake1M, while it performs exceptionally on FakeAVCeleb and LAV-DF. On the Temporal Forgery Localization task, it outperforms the state-of-the-art by 47.88 AP@0.75 on AV-Deepfake1M, and performs on-par on LAV-DF. Code available at https://github.com/mever-team/dimodif.

Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos et al.

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 datasets and methods for multimodal misinformation detection (MMD). Due to the scarcity of large-scale annotated MMD datasets, recent approaches rely on synthetic training data created via out-of-context pairings or named entity manipulations (e.g., altering names, dates, or locations). However, these often yield simplistic examples that lack real-world complexity, limiting model robustness. Meanwhile, Large Vision-Language Models (LVLMs) remain underexplored for generating diverse and realistic synthetic data for MMD. To address, we introduce "Miscaption This!", a collection of LVLM-generated miscaptioned image datasets. Additionally, we introduce "Latent Multimodal Reconstruction" (LAMAR), a network trained to reconstruct the embeddings of truthful captions, providing a strong auxiliary signal to guide detection. We explore various training strategies (end-to-end vs. large-scale pre-training) and integration mechanisms (direct, mask, gate, and attention). Extensive experiments show that models trained on "MisCaption This!" generalize better to real-world misinformation while LAMAR achieves new state-of-the-art on both NewsCLIPpings and VERITE benchmarks; highlighting the value of LVLM-generated data and reconstruction-based networks for advancing MMD. Our code is available at https://github.com/stevejpapad/miscaptioned-image-reconstruction

Christos Koutlis, Symeon Papadopoulos

With the rapid advancement of sophisticated synthetic audio-visual content, e.g., for subtle malicious manipulations, ensuring the integrity of digital media has become paramount. This work presents a novel approach to temporal localization of deepfakes by leveraging Audio-Visual Speech Representation Reconstruction (AuViRe). Specifically, our approach reconstructs speech representations from one modality (e.g., lip movements) based on the other (e.g., audio waveform). Cross-modal reconstruction is significantly more challenging in manipulated video segments, leading to amplified discrepancies, thereby providing robust discriminative cues for precise temporal forgery localization. AuViRe outperforms the state of the art by +8.9 AP@0.95 on LAV-DF, +9.6 AP@0.5 on AV-Deepfake1M, and +5.1 AUC on an in-the-wild experiment. Code available at https://github.com/mever-team/auvire.

Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos et al.

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 fragmented implementations and inconsistent evaluation practices. Disparate datasets and metrics used across studies complicate reproducibility, making it difficult to fairly assess and compare the effectiveness of various approaches. To overcome these limitations, we introduce the Visual Bias Mitigator (VB-Mitigator), an open-source framework designed to streamline the development, evaluation, and comparative analysis of visual bias mitigation techniques. VB-Mitigator offers a unified research environment encompassing 12 established mitigation methods, 7 diverse benchmark datasets. A key strength of VB-Mitigator is its extensibility, allowing for seamless integration of additional methods, datasets, metrics, and models. VB-Mitigator aims to accelerate research toward fairness-aware computer vision models by serving as a foundational codebase for the research community to develop and assess their approaches. To this end, we also recommend best evaluation practices and provide a comprehensive performance comparison among state-of-the-art methodologies.

Efthymia Amarantidou, Christos Koutlis, Symeon Papadopoulos et al.

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 Synthetic Image Detection (SID) solutions struggle on generated images sourced from the Internet, as these are often altered by compression and other operations. To address this, our research enhances SID by exploring data augmentation combinations, leveraging a genetic algorithm for optimal augmentation selection, and introducing a dual-criteria optimization approach. These methods significantly improve model performance under real-world perturbations. Our findings provide valuable insights for developing detection models capable of identifying synthetic images across varying qualities and transformations, with the best-performing model achieving a mean average precision increase of +22.53% compared to models without augmentations. The implementation is available at github.com/efthimia145/sid-composite-data-augmentation.

Thanasis Pantsios, Dimitrios Karageorgiou, Christos Koutlis et al.

The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existing detectors often suffer from performance degradation under distribution shifts and when encountering newly emerging generative models. In this work, we propose a data-centric continual adaptation framework for updating detectors in evolving environments. We show that both in-the-wild data and generator-driven data are essential for adapting detectors. We introduce an automated, weakly supervised pipeline for constructing in-the-wild datasets through fact-check article retrieval. Additionally, we demonstrate that incorporating even a small amount of generator-driven data during training enables effective adaptation to newly emerging models, while combining it with in-the-wild data within a continual learning framework enables robust adaptation and mitigates catastrophic forgetting. Extensive experiments on two state-of-the-art detectors show significant improvements of +9.14% and +8% in average accuracy, respectively.

Georgia Baltsou, Ioannis Sarridis, Christos Koutlis et al.

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 primarily focus on demographic factors such as age, gender, and skin tone, overlooking other crucial facial attributes like hairstyle and accessories. This narrow focus limits the diversity of the data and consequently the robustness of AI systems trained on them. This work aims to address this limitation by proposing a methodology for generating synthetic face image datasets that capture a broader spectrum of facial diversity. Specifically, our approach integrates a systematic prompt formulation strategy, encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories. These prompts guide a state-of-the-art text-to-image model in generating a comprehensive dataset of high-quality realistic images and can be used as an evaluation set in face analysis systems. Compared to existing datasets, our proposed dataset proves equally or more challenging in image classification tasks while being much smaller in size.

Despina Konstantinidou, Dimitrios Karageorgiou, Christos Koutlis et al.

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 concerns, the challenge of AI-Generated Image Detection (AID) becomes increasingly critical. As these technologies become more sophisticated, the quality of AI-generated images has reached a level that can easily deceive even the most discerning observers. Our systematic evaluation highlights a critical weakness in current AI-Generated Image Detection models: while they perform exceptionally well on controlled benchmark datasets, they struggle significantly with real-world variations. To assess this, we introduce ITW-SM, a new dataset of real and AI-generated images collected from major social media platforms. In this paper, we identify four key factors that influence AID performance in real-world scenarios: backbone architecture, training data composition, pre-processing strategies and data augmentation combinations. By systematically analyzing these components, we shed light on their impact on detection efficacy. Our modifications result in an average AUC improvement of 26.87% across various AID models under real-world conditions.

Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos et al.

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 visual datasets where multiple, possibly unknown biases exist. To address this limitation, we introduce MAVias, an open-set bias mitigation approach leveraging foundation models to discover spurious associations between visual attributes and target classes. MAVias first captures a wide variety of visual features in natural language via a foundation image tagging model, and then leverages a large language model to select those visual features defining the target class, resulting in a set of language-coded potential visual biases. We then translate this set of potential biases into vision-language embeddings and introduce an in-processing bias mitigation approach to prevent the model from encoding information related to them. Our experiments on diverse datasets, including CelebA, Waterbirds, ImageNet, and UrbanCars, show that MAVias effectively detects and mitigates a wide range of biases in visual recognition tasks outperforming current state-of-the-art.

Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos et al.

EXplainable Artificial Intelligence (XAI) approaches are widely applied for identifying fairness issues in Artificial Intelligence (AI) systems. However, in the context of facial analysis, existing XAI approaches, such as pixel attribution methods, offer explanations for individual images, posing challenges in assessing the overall behavior of a model, which would require labor-intensive manual inspection of a very large number of instances and leaving to the human the task of drawing a general impression of the model behavior from the individual outputs. Addressing this limitation, we introduce FaceX, the first method that provides a comprehensive understanding of face attribute classifiers through summary model explanations. Specifically, FaceX leverages the presence of distinct regions across all facial images to compute a region-level aggregation of model activations, allowing for the visualization of the model's region attribution across 19 predefined regions of interest in facial images, such as hair, ears, or skin. Beyond spatial explanations, FaceX enhances interpretability by visualizing specific image patches with the highest impact on the model's decisions for each facial region within a test benchmark. Through extensive evaluation in various experimental setups, including scenarios with or without intentional biases and mitigation efforts on four benchmarks, namely CelebA, FairFace, CelebAMask-HQ, and Racial Faces in the Wild, FaceX demonstrates high effectiveness in identifying the models' biases.

Georgia Baltsou, Ioannis Sarridis, Christos Koutlis et al.

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 biases related to race, gender, and other demographic characteristics, limiting the effectiveness and fairness of face verification systems. In response to these challenges, we propose a comprehensive methodology that integrates advanced generative models to create varied and diverse high-quality synthetic face images. This methodology emphasizes the representation of a diverse range of facial traits, ensuring adherence to characteristics permissible in identity card photographs. Furthermore, we introduce the Diverse and Inclusive Faces for Verification (DIF-V) dataset, comprising 27,780 images of 926 unique identities, designed as a benchmark for future research in face verification. Our analysis reveals that existing verification models exhibit biases toward certain genders and races, and notably, applying identity style modifications negatively impacts model performance. By tackling the inherent inequities in existing datasets, this work not only enriches the discussion on diversity and ethics in artificial intelligence but also lays the foundation for developing more inclusive and reliable face verification technologies

Christos Koutlis, Symeon Papadopoulos, Manos Schinas et al.

Multivariate time series forecasting is of great importance to many scientific disciplines and industrial sectors. The evolution of a multivariate time series depends on the dynamics of its variables and the connectivity network of causal interrelationships among them. Most of the existing time series models do not account for the causal effects among the system's variables and even if they do they rely just on determining the between-variables causality network. Knowing the structure of such a complex network and even more specifically knowing the exact lagged variables that contribute to the underlying process is crucial for the task of multivariate time series forecasting. The latter is a rather unexplored source of information to leverage. In this direction, here a novel neural network-based architecture is proposed, termed LAgged VAriable Representation NETwork (LAVARNET), which intrinsically estimates the importance of lagged variables and combines high dimensional latent representations of them to predict future values of time series. Our model is compared with other baseline and state of the art neural network architectures on one simulated data set and four real data sets from meteorology, music, solar activity, and finance areas. The proposed architecture outperforms the competitive architectures in most of the experiments.