Pablo García Fernández

Assistant Professor

I am Pablo García Fernández, an Assistant Professor in Computer Science and Artificial Intelligence at the University of Santiago de Compostela (USC) and a researcher at the Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS). I received my PhD in 2025 with a dissertation on object detection under minimal supervision.

My research focuses on developing adaptable visual recognition systems that can operate beyond fixed category sets and with limited supervision, with particular interests in open-vocabulary object detection, few-shot learning, and multimodal visual recognition. I have also worked on transferring open-vocabulary models to X-ray imagery for security screening applications.

In 2024–2025, I was a visiting PhD researcher at the University of Trento (Italy), where I worked with the Multimedia and Human Understanding Group (MHUG).

During my PhD, I was awarded an FPU Predoctoral Fellowship from the Spanish Ministry of Universities, a highly competitive national fellowship supporting doctoral research in Spain.

My research has been published in international venues including ICCV.

selected publications

Superpowering Open-Vocabulary Object Detectors for X-ray Vision

Pablo Garcia-Fernandez, Lorenzo Vaquero, Mingxuan Liu, and 5 more authors

In IEEE International Conference on Computer Vision (ICCV), 2025

Abs Bib PDF Website

Open-vocabulary object detection (OvOD) is set to revolutionize security screening by enabling systems to recog nize 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.
@inproceedings{garcia2025superpowering, title = {Superpowering Open-Vocabulary Object Detectors for X-ray Vision}, author = {Garcia-Fernandez, Pablo and Vaquero, Lorenzo and Liu, Mingxuan and Xue, Feng and Cores, Daniel and Sebe, Nicu and Mucientes, Manuel and Ricci, Elisa}, booktitle = {IEEE International Conference on Computer Vision (ICCV)}, year = {2025}, }