I am a PhD student in Computer Vision at the University of Barcelona. My research interests include computer vision, deep learning and artificial intelligence. I work under the supervision of Dr. Petia Ivanova Radeva.
PhD in Computer Vision, TBD
University of Barcelona
MSc in Artificial Intelligence, 2023
Polytechnic University of Catalonia (UPC)
BSc in Computer Science, 2020
University of Murcia
BSc in Mathematics, 2020
University of Murcia
[29/10/2023] Very excited to present our work Dining on Details at MADiMa'23 in ACM Multimedia! 🇨🇦 🚀
[01/10/2023] We go to Paris to attend ICCV'23 and present a bunch of interesting projects! 🇫🇷 🚀
[19/09/2023] We presented a poster of our work Dining on Details at the 10th ACMCV in the Computer Vision Center.
Dining on Details (DoD) is an innovative fine-grained food classification approach using large language models to sort dataset classes into subsets. Powered by the robust ImageBind embedding space, DoD excels in distinguishing similar classes. Universally compatible, DoD integrates seamlessly with any existing classification architecture. Extensive testing on various food datasets and backbones shows performance boosts of 0.5% to 1.61%, and even achieves SoTA results on the Food-101 dataset.
Our new framework, “Mending Neighbours,” improves contrastive learning by effectively identifying and replacing unhelpful ’neighbour’ representations with our unique “Bridge Points”. This unsupervised method enhances model performance by ensuring only the most informative representations are learned. Outperforming leading methods on three benchmark datasets, our work underscores the crucial role of careful neighbour selection in contrastive learning.