Mikel Galar

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

Demographic biases in source datasets have been shown as one of the causes of unfairness and discrimination in the predictions of Machine Learning models. One of the most prominent types of demographic bias are statistical imbalances in the representation of demographic groups in the datasets. In this paper, we study the measurement of these biases by reviewing the existing metrics, including those that can be borrowed from other disciplines. We develop a taxonomy for the classification of these metrics, providing a practical guide for the selection of appropriate metrics. To illustrate the utility of our framework, and to further understand the practical characteristics of the metrics, we conduct a case study of 20 datasets used in Facial Emotion Recognition (FER), analyzing the biases present in them. Our experimental results show that many metrics are redundant and that a reduced subset of metrics may be sufficient to measure the amount of demographic bias. The paper provides valuable insights for researchers in AI and related fields to mitigate dataset bias and improve the fairness and accuracy of AI models. The code is available at https://github.com/irisdominguez/dataset_bias_metrics.

Juan Francisco Amieva, Christian Ayala, Roberto Del Prete et al.

Synthetic Aperture Radar (SAR) imagery enables all-weather, day-and-night Earth observation; however, it remains difficult to interpret due to speckle noise and other intrinsic imaging artifacts. Sentinel-1 (S1) constitutes one of the most widely used spaceborne SAR missions, offering systematic global coverage, high temporal resolution, dual-polarization imaging, and free data availability. Among S1 modes, Stripmap (SM) provides the highest resolution, yet speckle noise and spatial constraints often hinder applications requiring finer spatial detail. This motivates the need for effective image enhancement strategies. In this work, we propose a self-supervised enhancement framework for S1 SM imagery based on azimuth subaperture decomposition. The method exploits the physical consistency between subaperture reconstructions and the corresponding full-aperture image to generate paired training data without external sensors, simulated ground truth, or multi-temporal stacks. The proposed framework integrates single- and multi-frame learning and incorporates an iterative inference scheme that progressively refines image quality. Experiments on real S1 SM data show that the proposed approach consistently outperforms the widely adopted self-supervised deep learning baseline MERLIN, in terms of PSNR and SSIM, while MERLIN attains higher ENL, highlighting a trade-off between structural fidelity and speckle smoothing. Overall, the results demonstrate that subaperture-based supervision provides a physically grounded, reproducible, and operationally viable approach for SAR image enhancement using S1 data. It is worth noting that the proposed approach can be extended to other SAR platforms, polarizations, and acquisition modes.

Marco D'Alessandro, Alberto Alonso, Enrique Calabrés et al.

Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions. To succeed in this task, it is necessary to avoid over-fitting new classes caused by biased distributions in the few-shot training sets. The general approach to address this issue involves enhancing the representational capability of a pre-defined backbone architecture by adding special modules for backward compatibility with older classes. However, this approach has not yet solved the dilemma of ensuring high classification accuracy over time while reducing the gap between the performance obtained on larger training sets and the smaller ones. In this work, we propose an alternative approach called Continual Parameter-Efficient CLIP (CPE-CLIP) to reduce the loss of information between different learning sessions. Instead of adapting additional modules to address information loss, we leverage the vast knowledge acquired by CLIP in large-scale pre-training and its effectiveness in generalizing to new concepts. Our approach is multimodal and parameter-efficient, relying on learnable prompts for both the language and vision encoders to enable transfer learning across sessions. We also introduce prompt regularization to improve performance and prevent forgetting. Our experimental results demonstrate that CPE-CLIP significantly improves FSCIL performance compared to state-of-the-art proposals while also drastically reducing the number of learnable parameters and training costs.

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

The increasing amount of applications of Artificial Intelligence (AI) has led researchers to study the social impact of these technologies and evaluate their fairness. Unfortunately, current fairness metrics are hard to apply in multi-class multi-demographic classification problems, such as Facial Expression Recognition (FER). We propose a new set of metrics to approach these problems. Of the three metrics proposed, two focus on the representational and stereotypical bias of the dataset, and the third one on the residual bias of the trained model. These metrics combined can potentially be used to study and compare diverse bias mitigation methods. We demonstrate the usefulness of the metrics by applying them to a FER problem based on the popular Affectnet dataset. Like many other datasets for FER, Affectnet is a large Internet-sourced dataset with 291,651 labeled images. Obtaining images from the Internet raises some concerns over the fairness of any system trained on this data and its ability to generalize properly to diverse populations. We first analyze the dataset and some variants, finding substantial racial bias and gender stereotypes. We then extract several subsets with different demographic properties and train a model on each one, observing the amount of residual bias in the different setups. We also provide a second analysis on a different dataset, FER+.

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

Facial Expression Recognition (FER) uses images of faces to identify the emotional state of users, allowing for a closer interaction between humans and autonomous systems. Unfortunately, as the images naturally integrate some demographic information, such as apparent age, gender, and race of the subject, these systems are prone to demographic bias issues. In recent years, machine learning-based models have become the most popular approach to FER. These models require training on large datasets of facial expression images, and their generalization capabilities are strongly related to the characteristics of the dataset. In publicly available FER datasets, apparent gender representation is usually mostly balanced, but their representation in the individual label is not, embedding social stereotypes into the datasets and generating a potential for harm. Although this type of bias has been overlooked so far, it is important to understand the impact it may have in the context of FER. To do so, we use a popular FER dataset, FER+, to generate derivative datasets with different amounts of stereotypical bias by altering the gender proportions of certain labels. We then proceed to measure the discrepancy between the performance of the models trained on these datasets for the apparent gender groups. We observe a discrepancy in the recognition of certain emotions between genders of up to $29 \%$ under the worst bias conditions. Our results also suggest a safety range for stereotypical bias in a dataset that does not appear to produce stereotypical bias in the resulting model. Our findings support the need for a thorough bias analysis of public datasets in problems like FER, where a global balance of demographic representation can still hide other types of bias that harm certain demographic groups.

Francesco Zola, Jose Alvaro Fernandez-Carrasco, Jan Lukas Bruse et al.

Biometric systems represent valid solutions in tasks like user authentication and verification, since they are able to analyze physical and behavioural features with high precision. However, especially when physical biometrics are used, as is the case of iris recognition, they require specific hardware such as retina scanners, sensors, or HD cameras to achieve relevant results. At the same time, they require the users to be very close to the camera to extract high-resolution information. For this reason, in this work, we propose a novel approach that uses long-range (LR) distance images for implementing an iris verification system. More specifically, we present a novel methodology for converting LR iris images into graphs and then use Graph Siamese Neural Networks (GSNN) to predict whether two graphs belong to the same person. In this study, we not only describe this methodology but also evaluate how the spectral components of these images can be used for improving the graph extraction and the final classification task. Results demonstrate the suitability of this approach, encouraging the community to explore graph application in biometric systems.

Alex Salvatierra, José Antonio Sanz, Christian Gutiérrez et al.

Recent advances in deep learning have significantly improved 3D semantic segmentation, but most models focus on indoor or terrestrial datasets. Their behavior under real aerial acquisition conditions remains insufficiently explored, and although a few studies have addressed similar scenarios, they differ in dataset design, acquisition conditions, and model selection. To address this gap, we conduct an experimental benchmark evaluating several state-of-the-art architectures on a large-scale aerial LiDAR dataset acquired under operational flight conditions in Navarre, Spain, covering heterogeneous urban, rural, and industrial landscapes. This study compares four representative deep learning models, including KPConv, RandLA-Net, Superpoint Transformer, and Point Transformer V3, across five semantic classes commonly found in airborne surveys, such as ground, vegetation, buildings, and vehicles, highlighting the inherent challenges of class imbalance and geometric variability in aerial data. Results show that all tested models achieve high overall accuracy exceeding 93%, with KPConv attaining the highest mean IoU (78.51%) through consistent performance across classes, particularly on challenging and underrepresented categories. Point Transformer V3 demonstrates superior performance on the underrepresented vehicle class (75.11% IoU), while Superpoint Transformer and RandLA-Net trade off segmentation robustness for computational efficiency.

Alex Salvatierra, José Antonio Sanz, Christian Gutiérrez et al.

Semantic segmentation metrics for 3D point clouds, such as mean Intersection over Union (mIoU) and Overall Accuracy (OA), present two key limitations in the context of aerial LiDAR data. First, they treat all misclassifications equally regardless of their spatial context, overlooking cases where the geometric severity of errors directly impacts the quality of derived geospatial products such as Digital Terrain Models. Second, they are often dominated by the large proportion of easily classified points, which can mask meaningful differences between models and under-represent performance in challenging regions. To address these limitations, we propose a novel evaluation framework for comparing semantic segmentation models through two complementary approaches. First, we introduce distance-based metrics that account for the spatial deviation between each misclassified point and the nearest ground-truth point of the predicted class, capturing the geometric severity of errors. Second, we propose a focused evaluation on a common subset of hard points, defined as the points misclassified by at least one of the evaluated models, thereby reducing the bias introduced by easily classified points and better revealing differences in model performance in challenging regions. We validate our framework by comparing three state-of-the-art deep learning models on three aerial LiDAR datasets. Results demonstrate that the proposed metrics provide complementary information to traditional measures, revealing spatial error patterns that are critical for Earth Observation applications but invisible to conventional evaluation approaches. The proposed framework enables more informed model selection for scenarios where spatial consistency is critical.

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

In the last few years, Artificial Intelligence systems have become increasingly widespread. Unfortunately, these systems can share many biases with human decision-making, including demographic biases. Often, these biases can be traced back to the data used for training, where large uncurated datasets have become the norm. Despite our knowledge of these biases, we still lack general tools to detect and quantify them, as well as to compare the biases in different datasets. Thus, in this work, we propose DSAP (Demographic Similarity from Auxiliary Profiles), a two-step methodology for comparing the demographic composition of two datasets. DSAP can be deployed in three key applications: to detect and characterize demographic blind spots and bias issues across datasets, to measure dataset demographic bias in single datasets, and to measure dataset demographic shift in deployment scenarios. An essential feature of DSAP is its ability to robustly analyze datasets without explicit demographic labels, offering simplicity and interpretability for a wide range of situations. To show the usefulness of the proposed methodology, we consider the Facial Expression Recognition task, where demographic bias has previously been found. The three applications are studied over a set of twenty datasets with varying properties. The code is available at https://github.com/irisdominguez/DSAP.

Ruben Pascual, Inés Hernández, Salvador Gutiérrez et al.

Variability in illumination is a primary factor limiting deep learning robustness for field-based plant disease detection. This study evaluates Histogram Matching (HM), a technique that transforms the pixel intensity distribution of an image to match a reference profile, to mitigate this in grapevine classification, distinguishing among healthy leaves, downy mildew, and spider mite damage. We propose a dual-stage integration of HM: (i) as a preprocessing step for normalization, and (ii) as a data augmentation technique to introduce controlled training variability. Experiments using 1,469 RGB images (comprising homogeneous leaf-focused and heterogeneous canopy samples) to train ResNet-18 models demonstrate that this combination significantly enhances robustness on real-world canopy images. While leaf-focused samples showed marginal gains, the canopy subset improved markedly, indicating that balancing normalization with histogram-based diversification effectively bridges the domain gap caused by uncontrolled lighting.

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar et al.

In recent years, the rapid development of artificial intelligence (AI) systems has raised concerns about our ability to ensure their fairness, that is, how to avoid discrimination based on protected characteristics such as gender, race, or age. While algorithmic fairness is well-studied in simple binary classification tasks on tabular data, its application to complex, real-world scenarios-such as Facial Expression Recognition (FER)-remains underexplored. FER presents unique challenges: it is inherently multiclass, and biases emerge across intersecting demographic variables, each potentially comprising multiple protected groups. We present a comprehensive framework to analyze bias propagation from datasets to trained models in image-based FER systems, while introducing new bias metrics specifically designed for multiclass problems with multiple demographic groups. Our methodology studies bias propagation by (1) inducing controlled biases in FER datasets, (2) training models on these biased datasets, and (3) analyzing the correlation between dataset bias metrics and model fairness notions. Our findings reveal that stereotypical biases propagate more strongly to model predictions than representational biases, suggesting that preventing emotion-specific demographic patterns should be prioritized over general demographic balance in FER datasets. Additionally, we observe that biased datasets lead to reduced model accuracy, challenging the assumed fairness-accuracy trade-off.

Ruben Pascual, Mikel Sesma-Sara, Aranzazu Jurio et al.

The audiovisual industry is undergoing a profound transformation as it is integrating AI developments not only to automate routine tasks but also to inspire new forms of art. This paper addresses the problem of producing a virtually unlimited number of novel characters that preserve the artistic style and shared visual traits of a small set of human-designed reference characters, thus broadening creative possibilities in animation, gaming, and related domains. Our solution builds upon DreamBooth, a well-established fine-tuning technique for text-to-image diffusion models, and adapts it to tackle two core challenges: capturing intricate character details beyond textual prompts and the few-shot nature of the training data. To achieve this, we propose a multi-token strategy, using clustering to assign separate tokens to individual characters and their collective style, combined with LoRA-based parameter-efficient fine-tuning. By removing the class-specific regularization set and introducing random tokens and embeddings during generation, our approach allows for unlimited character creation while preserving the learned style. We evaluate our method on five small specialized datasets, comparing it to relevant baselines using both quantitative metrics and a human evaluation study. Our results demonstrate that our approach produces high-quality, diverse characters while preserving the distinctive aesthetic features of the reference characters, with human evaluation further reinforcing its effectiveness and highlighting the potential of our method.

Iris Dominguez-Catena, Daniel Paternain, Aranzazu Jurio et al.

Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This is particularly concerning with the increasing use of large, unsupervised datasets for training foundational models. Traditionally, demographic biases within these datasets have not been well-understood, limiting our ability to understand how they propagate to the models themselves. To address this issue, this paper investigates the propagation of demographic biases from datasets into machine learning models. We focus on the gender demographic component, analyzing two types of bias: representational and stereotypical. For our analysis, we consider the domain of facial expression recognition (FER), a field known to exhibit biases in most popular datasets. We use Affectnet, one of the largest FER datasets, as our baseline for carefully designing and generating subsets that incorporate varying strengths of both representational and stereotypical bias. Subsequently, we train several models on these biased subsets, evaluating their performance on a common test set to assess the propagation of bias into the models' predictions. Our results show that representational bias has a weaker impact than expected. Models exhibit a good generalization ability even in the absence of one gender in the training dataset. Conversely, stereotypical bias has a significantly stronger impact, primarily concentrated on the biased class, although it can also influence predictions for unbiased classes. These results highlight the need for a bias analysis that differentiates between types of bias, which is crucial for the development of effective bias mitigation strategies.

Francesco Zola, Jan Lukas Bruse, Xabier Etxeberria Barrio et al.

In Bitcoin entity classification, results are strongly conditioned by the ground-truth dataset, especially when applying supervised machine learning approaches. However, these ground-truth datasets are frequently affected by significant class imbalance as generally they contain much more information regarding legal services (Exchange, Gambling), than regarding services that may be related to illicit activities (Mixer, Service). Class imbalance increases the complexity of applying machine learning techniques and reduces the quality of classification results, especially for underrepresented, but critical classes. In this paper, we propose to address this problem by using Generative Adversarial Networks (GANs) for Bitcoin data augmentation as GANs recently have shown promising results in the domain of image classification. However, there is no "one-fits-all" GAN solution that works for every scenario. In fact, setting GAN training parameters is non-trivial and heavily affects the quality of the generated synthetic data. We therefore evaluate how GAN parameters such as the optimization function, the size of the dataset and the chosen batch size affect GAN implementation for one underrepresented entity class (Mining Pool) and demonstrate how a "good" GAN configuration can be obtained that achieves high similarity between synthetically generated and real Bitcoin address data. To the best of our knowledge, this is the first study presenting GANs as a valid tool for generating synthetic address data for data augmentation in Bitcoin entity classification.

Mikel Elkano, Humberto Bustince, Mikel Galar

The Era of Big Data has forced researchers to explore new distributed solutions for building fuzzy classifiers, which often introduce approximation errors or make strong assumptions to reduce computational and memory requirements. As a result, Big Data classifiers might be expected to be inferior to those designed for standard classification tasks (Small Data) in terms of accuracy and model complexity. To our knowledge, however, there is no empirical evidence to confirm such a conjecture yet. Here, we investigate the extent to which state-of-the-art fuzzy classifiers for Big Data sacrifice performance in favor of scalability. To this end, we carry out an empirical study that compares these classifiers with some of the best performing algorithms for Small Data. Assuming the latter were generally designed for maximizing performance without considering scalability issues, the results of this study provide some intuition around the tradeoff between performance and scalability achieved by current Big Data solutions. Our findings show that, although slightly inferior, Big Data classifiers are gradually catching up with state-of-the-art classifiers for Small data, suggesting that a unified learning algorithm for Big and Small Data might be possible.

Mikel Elkano, Mikel Uriz, Humberto Bustince et al.

We present a new distributed fuzzy partitioning method to reduce the complexity of multi-way fuzzy decision trees in Big Data classification problems. The proposed algorithm builds a fixed number of fuzzy sets for all variables and adjusts their shape and position to the real distribution of training data. A two-step process is applied : 1) transformation of the original distribution into a standard uniform distribution by means of the probability integral transform. Since the original distribution is generally unknown, the cumulative distribution function is approximated by computing the q-quantiles of the training set; 2) construction of a Ruspini strong fuzzy partition in the transformed attribute space using a fixed number of equally distributed triangular membership functions. Despite the aforementioned transformation, the definition of every fuzzy set in the original space can be recovered by applying the inverse cumulative distribution function (also known as quantile function). The experimental results reveal that the proposed methodology allows the state-of-the-art multi-way fuzzy decision tree (FMDT) induction algorithm to maintain classification accuracy with up to 6 million fewer leaves.

Mikel Elkano, Jose Sanz, Edurne Barrenechea et al.

Interpretability has always been a major concern for fuzzy rule-based classifiers. The usage of human-readable models allows them to explain the reasoning behind their predictions and decisions. However, when it comes to Big Data classification problems, fuzzy rule-based classifiers have not been able to maintain the good trade-off between accuracy and interpretability that has characterized these techniques in non-Big Data environments. The most accurate methods build too complex models composed of a large number of rules and fuzzy sets, while those approaches focusing on interpretability do not provide state-of-the-art discrimination capabilities. In this paper, we propose a new distributed learning algorithm named CFM-BD to construct accurate and compact fuzzy rule-based classification systems for Big Data. This method has been specifically designed from scratch for Big Data problems and does not adapt or extend any existing algorithm. The proposed learning process consists of three stages: 1) pre-processing based on the probability integral transform theorem; 2) rule induction inspired by CHI-BD and Apriori algorithms; 3) rule selection by means of a global evolutionary optimization. We conducted a complete empirical study to test the performance of our approach in terms of accuracy, complexity, and runtime. The results obtained were compared and contrasted with four state-of-the-art fuzzy classifiers for Big Data (FBDT, FMDT, Chi-Spark-RS, and CHI-BD). According to this study, CFM-BD is able to provide competitive discrimination capabilities using significantly simpler models composed of a few rules of less than 3 antecedents, employing 5 linguistic labels for all variables.