Pasar al contenido principal

APROVECHANDO LA INTELIGENCIA ARTIFICIAL PARA UNA MONITORIZACION PREDICTIVA ROBUSTA EN MINERIA DE PROCESOS

PID2023-149549NB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDADE DE SANTIAGO DE COMPOSTELA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Capítulo o parte de un libro (BookPart)

Lost in Time: A New Temporal Benchmark for VideoLLMs

  • Cores Costa, Daniel
  • Dorkenwald, Michael
  • Mucientes Molina, Manuel
  • Snoek, Cess G. M.
  • Asano, Yuki M.
Large language models have demonstrated impressive performance when integrated with vision models even enabling video understanding. However, evaluating video models presents its own unique challenges, for which several benchmarks have been proposed. In this paper, we show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning. We identified three main issues in existing datasets: (i) static information from single frames is often sufficient to solve the tasks (ii) the text of the questions and candidate answers is overly informative, allowing models to answer correctly without relying on any visual input (iii) world knowledge alone can answer many of the questions, making the benchmarks a test of knowledge replication rather than video reasoning. In addition, we found that open-ended question-answering benchmarks for video understanding suffer from similar issues while the automatic evaluation process with LLMs is unreliable, making it an unsuitable alternative. As a solution, we propose TVBench, a novel open-source video multiple-choice question-answering benchmark, and demonstrate through extensive evaluations that it requires a high level of temporal understanding. Surprisingly, we find that many recent video-language models perform similarly to random performance on TVBench, with only a few models such as Aria, Qwen2-VL, and Tarsier surpassing this baseline.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

Enhancing few-shot object detection through pseudo-label mining

  • García Fernández, Pablo
  • Cores Costa, Daniel
  • Mucientes Molina, Manuel
Few-shot object detection involves adapting an existing detector to a set of unseen categories with few annotated examples. This data limitation makes these methods to underperform those trained on large labeled datasets. In many scenarios, there is a high amount of unlabeled data that is never exploited. Thus, we propose to exPAND the initial novel set by mining pseudo-labels. From a raw set of detections, xPAND obtains reliable pseudo-labels suitable for training any detector. To this end, we propose two new modules: Class and Box confirmation. Class Confirmation aims to remove misclassified pseudo-labels by comparing candidates with expected class prototypes. Box Confirmation estimates IoU to discard inadequately framed objects. Experimental results demonstrate that xPAND enhances the performance of multiple detectors up to +5.9 nAP and +16.4 nAP50 points for MS-COCO and PASCAL VOC, respectively, establishing a new state of the art. Code: https://github.com/PAGF188/xPAND
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

From Genesis to Maturity: Managing Knowledge Graph Ecosystems Through Life Cycles

  • Geisler, Sandra
  • Cappiello, Cinzia
  • Celino, Irene
  • Chaves Fraga, David
  • Dimou, Anastasia
  • Iglesias-Molina, Ana
  • Lenzerini, Maurizio
  • Rula, Anisa
  • Van Assche, Dylan
  • Welten, Sascha
  • Vidal, Maria-Esther
Knowledge graphs (KGs) play a crucial role in the integration and organization of heterogeneous data and knowledge, enabling advanced data analytics and decision-making across various industries. This vision paper addresses critical challenges in managing KGs, emphasizing their relevance in integrating information from disparate sources. We propose the concept of knowledge graph ecosystems and life cycles to systematically manage tasks, e.g., data integration, standardization, continuous updates, efficient querying, and provenance tracking. By adopting our approach, organizations can enhance the accuracy, consistency, and reliability of KGs, thus improving knowledge management, enabling the extraction of valuable insights, and ensuring transparency and accountability.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

DeclareAligner: A leap towards efficient optimal alignments for declarative process model conformance checking

  • Casas Ramos, Jacobo
  • Lama Penín, Manuel
  • Mucientes Molina, Manuel
Conformance checking is a crucial aspect of process mining, enabling organizations to identify deviations between actual process behavior and modeled expectations. At the heart of conformance checking lies the concept of optimal alignments, which provide a detailed, cost-minimized mapping of observed behavior to expected behavior. Optimal alignments facilitate the identification of root causes of non-conformity and guide corrective actions. This is a critical area where Artificial Intelligence (AI) plays a pivotal role in driving effective process improvement. However, computing optimal alignments poses significant computational challenges due to the vast search space inherent in declarative process models. Consequently, existing approaches often struggle with scalability and efficiency, limiting their applicability in real-world settings. This paper introduces DeclareAligner, a novel algorithm that uses the A* search algorithm, an established AI pathfinding technique, to tackle the problem from a fresh perspective leveraging the flexibility of declarative models. Key features of DeclareAligner include only performing actions that actively contribute to fixing constraint violations, utilizing a tailored heuristic to navigate towards optimal solutions, and employing early pruning to eliminate unproductive branches, while also streamlining the process through preprocessing and consolidating multiple fixes into unified actions. The proposed method is evaluated using 8054 synthetic and real-life alignment problems, demonstrating its ability to efficiently compute optimal alignments by significantly outperforming the current state of the art. By enabling process analysts to more effectively identify and understand conformance issues, DeclareAligner has the potential to drive meaningful process improvement and management.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Capítulo o parte de un libro (BookPart)

MixUDA: From Synthetic to Real Object Detection

  • Gil Pérez, Pablo
  • Cores Costa, Daniel
  • Mucientes Molina, Manuel
Object detection has made remarkable progress in recent years, driven by advancements in deep learning and the availability of large-scale annotated datasets. However, these methods often require extensive labeled data, which may not be accessible for specific or emerging applications. This limitation has generated interest in Unsupervised Domain Adaptation (UDA), which facilitates knowledge transfer from a labeled source domain to an unlabeled and differently distributed target domain. This study addresses the challenge of UDA between synthetic and realworld data. A methodology for generating synthetic datasets is proposed using AirSim and Unreal Engine, enabling the creation of highly customizable and diverse datasets. We also propose a Domain Adaptation technique, MixUDA, that maximizes the utility of the synthetic dataset to improve the performance of a model in a real domain. MixUDA is a UDA approach which uses a Mean Teacher architecture and employs pseudo-labels combined with two different image-mixing operations to achieve a smooth and progressive transition from the synthetic to the real domain: pseudo-mosaic and pseudo-mixup. The obtained results demonstrate encouraging progress, as MixUDA surpasses state-of-the-art models D3T and MixPL by 1.18 and 4 AP points respectively, approaching performance of oracle models trained directly on the target domain. These findings suggest that synthetic datasets have significant potential in addressing data scarcity and improving model generalization, while also pointing to promising directions for further exploration in this area.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

Trustworthy Data-driven Chronological Age Estimation from Panoramic Dental Images

  • Vivel Couso, Ainhoa
  • Vila Blanco, Nicolás
  • Carreira Nouche, María José
  • Bugarín-Diz, Alberto
  • Tomás Carmona, Inmaculada
  • Alonso Moral, José María
Integrating deep learning into healthcare enables personalized care but raises trust issues due to model opacity. To improve transparency, we propose a system for dental age estimation from panoramic images that combines an opaque and a transparent method within a natural language generation (NLG) module. This module produces clinician-friendly textual explanations about the age estimations, designed with dental experts through a rule-based approach. Following the best practices in the field, the quality of the generated explanations was manually validated by dental experts using a questionnaire. The results showed a strong performance, since the experts rated 4.77$\pm$0.12 (out of 5) on average across the five dimensions considered. We also performed a trustworthy self-assessment procedure following the ALTAI checklist, in which it scored 4.40$\pm$0.27 (out of 5) across seven dimensions of the AI Trustworthiness Assessment List.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Contribución de congreso (ConferenceOutput)

Superpowering Open-Vocabulary Object Detectors for X-ray Vision

  • García Fernández, Pablo
  • Vaquero Otal, Lorenzo
  • Liu, Mingxuan
  • Xue, Feng
  • Cores Costa, Daniel
  • Sebe, Nicu
  • Mucientes Molina, Manuel
  • Ricci, Elisa
Open-vocabulary object detection (OvOD) is set to revolutionize security screening by enabling systems to recognize any item in X-ray scans. However, developing effective OvOD models for X-ray imaging presents unique challenges due to data scarcity and the modality gap that prevents direct adoption of RGB-based solutions. To overcome these limitations, we propose RAXO, a training-free framework that repurposes off-the-shelf RGB OvOD detectors for robust X-ray detection. RAXO builds high-quality X-ray class descriptors using a dual-source retrieval strategy. It gathers relevant RGB images from the web and enriches them via a novel X-ray material transfer mechanism, eliminating the need for labeled databases. These visual descriptors replace text-based classification in OvOD, leveraging intra-modal feature distances for robust detection. Extensive experiments demonstrate that RAXO consistently improves OvOD performance, providing an average mAP increase of up to 17.0 points over base detectors. To further support research in this emerging field, we also introduce DET-COMPASS, a new benchmark featuring bounding box annotations for over 300 object categories, enabling large-scale evaluation of OvOD in X-ray.
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Capítulo o parte de un libro (BookPart)

Exploring Open-Vocabulary Models for Category-Free Detection

  • García Fernández, Pablo
  • Mucientes Molina, Manuel
  • Cores Costa, Daniel
Object detection models typically rely on a predefined setof categories, limiting their applicability in real-world scenarios whereobject classes may be unknown. In this paper, we propose a novel,training-free framework that enables off-the-shelf open-vocabulary ob-ject detectors (OvOD) to perform category-free detection —localizingand classifying objects without any prior category knowledge. Our ap-proach leverages image captioning to dynamically generate descriptiveterms directly from the image content, followed by a WordNet-based fil-tering process to extract semantically meaningful category names. Thesediscovered categories are then embedded and matched with visual regionfeatures using a frozen OvOD model to perform detection. We evaluateour method on the COCO dataset in a fully zero-shot setting and demon-strate that it significantly outperforms strong multimodal large languagemodel baselines, achieving an improvement of over 30 AP points. Thishighlights our method as a promising direction for more adaptive solu-tions to real-world detection challenges.