Artzai Picón

Artzai Picon, Pablo Galan, Arantza Bereciartua-Perez et al.

Hyperspectral imaging, a rapidly evolving field, has witnessed the ascendancy of deep learning techniques, supplanting classical feature extraction and classification methods in various applications. However, many researchers employ arbitrary architectures for hyperspectral image processing, often without rigorous analysis of the interplay between spectral and spatial information. This oversight neglects the implications of combining these two modalities on model performance. In this paper, we evaluate the performance of diverse deep learning architectures for hyperspectral image segmentation. Our analysis disentangles the impact of different architectures, spanning various spectral and spatial granularities. Specifically, we investigate the effects of spectral resolution (capturing spectral information) and spatial texture (conveying spatial details) on segmentation outcomes. Additionally, we explore the transferability of knowledge from large pre-trained image foundation models, originally designed for RGB images, to the hyperspectral domain. Results show that incorporating spatial information alongside spectral data leads to improved segmentation results, and that it is essential to further work on novel architectures comprising spectral and spatial information and on the adaption of RGB foundation models into the hyperspectral domain. Furthermore, we contribute to the field by cleaning and publicly releasing the Tecnalia WEEE Hyperspectral dataset. This dataset contains different non-ferrous fractions of Waste Electrical and Electronic Equipment (WEEE), including Copper, Brass, Aluminum, Stainless Steel, and White Copper, spanning the range of 400 to 1000 nm. We expect these conclusions can guide novel researchers in the field of hyperspectral imaging.

Leire Benito-Del-Valle, Artzai Picón, Daniel Mugica et al.

Herbicide field trials require accurate identification of plant species and assessment of herbicide-induced damage across diverse environments. While general-purpose vision foundation models have shown promising results in complex visual domains, their performance can be limited in agriculture, where fine-grained distinctions between species and damage types are critical. In this work, we adapt a general-purpose vision foundation model to herbicide trial characterization. Trained using a self-supervised learning approach on a large, curated agricultural dataset, the model learns rich and transferable representations optimized for herbicide trials images. Our domain-specific model significantly outperforms the best general-purpose foundation model in both species identification (F1 score improvement from 0.91 to 0.94) and damage classification (from 0.26 to 0.33). Under unseen conditions (new locations and other time), it achieves even greater gains (species identification from 0.56 to 0.66; damage classification from 0.17 to 0.27). In domain-shift scenarios, such as drone imagery, it maintains strong performance (species classification from 0.49 to 0.60). Additionally, we show that domain-specific pretraining enhances segmentation accuracy, particularly in low-annotation regimes. An annotation-efficiency analysis reveals that, under unseen conditions, the domain-specific model achieves 5.4% higher F1 score than the general-purpose model, while using 80% fewer labeled samples. These results demonstrate the generalization capabilities of domain-specific foundation models and their potential to significantly reduce manual annotation efforts, offering a scalable and automated solution for herbicide trial analysis.

Leire Benito-Del-Valle, Pedro A. Moreno-Sánchez, Itziar Egusquiza et al.

The MIDOG 2025 challenge extends prior work on mitotic figure detection by introducing a new Track 2 on atypical mitosis classification. This task aims to distinguish normal from atypical mitotic figures in histopathology images, a clinically relevant but highly imbalanced and cross-domain problem. We investigated two complementary backbones: (i) ConvNeXt-Small, pretrained on ImageNet, and (ii) a histopathology-specific ViT from Lunit trained via self-supervision. To address the strong prevalence imbalance (9408 normal vs. 1741 atypical), we synthesized additional atypical examples to approximate class balance and compared models trained with real-only vs. real+synthetic data. Using five-fold cross-validation, both backbones reached strong performance (mean AUROC approximately 95 percent), with ConvNeXt achieving slightly higher peaks while Lunit exhibited greater fold-to-fold stability. Synthetic balancing, however, did not lead to consistent improvements. On the organizers' preliminary hidden test set, explicitly designed as an out-of-distribution debug subset, ConvNeXt attained the highest AUROC (95.4 percent), whereas Lunit remained competitive on balanced accuracy. These findings suggest that both ImageNet and domain-pretrained backbones are viable for atypical mitosis classification, with domain-pretraining conferring robustness and ImageNet pretraining reaching higher peaks, while naive synthetic balancing has limited benefit. Full hidden test set results will be reported upon challenge completion.

Uxue Delaquintana-Aramendi, Leire Benito-del-Valle, Aitor Alvarez-Gila et al.

In colonoscopy, 80% of the missed polyps could be detected with the help of Deep Learning models. In the search for algorithms capable of addressing this challenge, foundation models emerge as promising candidates. Their zero-shot or few-shot learning capabilities, facilitate generalization to new data or tasks without extensive fine-tuning. A concept that is particularly advantageous in the medical imaging domain, where large annotated datasets for traditional training are scarce. In this context, a comprehensive evaluation of foundation models for polyp segmentation was conducted, assessing both detection and delimitation. For the study, three different colonoscopy datasets have been employed to compare the performance of five different foundation models, DINOv2, YOLO-World, GroundingDINO, SAM and MedSAM, against two benchmark networks, YOLOv8 and Mask R-CNN. Results show that the success of foundation models in polyp characterization is highly dependent on domain specialization. For optimal performance in medical applications, domain-specific models are essential, and generic models require fine-tuning to achieve effective results. Through this specialization, foundation models demonstrated superior performance compared to state-of-the-art detection and segmentation models, with some models even excelling in zero-shot evaluation; outperforming fine-tuned models on unseen data.

M. Shahriari, D. Pardo, J. A. Rivera et al.

Deep learning (DL) is a numerical method that approximates functions. Recently, its use has become attractive for the simulation and inversion of multiple problems in computational mechanics, including the inversion of borehole logging measurements for oil and gas applications. In this context, DL methods exhibit two key attractive features: a) once trained, they enable to solve an inverse problem in a fraction of a second, which is convenient for borehole geosteering operations as well as in other real-time inversion applications. b) DL methods exhibit a superior capability for approximating highly-complex functions across different areas of knowledge. Nevertheless, as it occurs with most numerical methods, DL also relies on expert design decisions that are problem specific to achieve reliable and robust results. Herein, we investigate two key aspects of deep neural networks (DNNs) when applied to the inversion of borehole resistivity measurements: error control and adequate selection of the loss function. As we illustrate via theoretical considerations and extensive numerical experiments, these interrelated aspects are critical to recover accurate inversion results.

Alfonso Medela, Artzai Picon

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling complex scenarios with the presence of many classes and scarcity on the number of images per class not only work to build classifiers, but to many other applications where measuring similarity is the key. Deep Neural Networks trained via metric learning also offer the possibility to solve few-shot learning problems. Currently used state of the art loss functions such as triplet and contrastive loss functions, still suffer from slow convergence due to the selection of effective training samples that has been partially solved by the multi-class N-pair loss by simultaneously adding additional samples from the different classes. In this work, we extend triplet and multiclass-N-pair loss function by proposing the constellation loss metric where the distances among all class combinations are simultaneously learned. We have compared our constellation loss for visual class embedding showing that our loss function over-performs the other methods by obtaining more compact clusters while achieving better classification results.

M. Shahriari, D. Pardo, A. Picón et al.

We use borehole resistivity measurements to map the electrical properties of the subsurface and to increase the productivity of a reservoir. When used for geosteering purposes, it becomes essential to invert them in real time. In this work, we explore the possibility of using Deep Neural Network (DNN) to perform a rapid inversion of borehole resistivity measurements. Herein, we build a DNN that approximates the following inverse problem: given a set of borehole resistivity measurements, the DNN is designed to deliver a physically meaningful and data-consistent piecewise one-dimensional layered model of the surrounding subsurface. Once the DNN is built, we can perform the actual inversion of the field measurements in real time. We illustrate the performance of DNN of logging-while-drilling measurements acquired on high-angle wells via synthetic data.