Self-supervised Learning from Images, and Augmentations

Abstract:  In this talk, Yuki M. Asano will talk about pushing the limits of what can be learnt without using any human annotations. After a first overview of what self-supervised learning is, we will first dive into how clustering can be combined with representation learning using optimal transport ([1] @ ICLR’20), a paradigm still relevant … Read more

Mobile World Congress 2023

The Mobile World Congress is back from February 27 to March 02 at Fira de Barcelona. The Computer Vision Center (CVC) will attend the congress within the Catalan Government Pavilion thanks to the support of the Generalitat de Catalunya. Our stand wants to be a meeting point where to discuss the potential role that computer … Read more

#100tífiques: promoting science and technology among young people and enhancing female role models

Several female scientists from the Computer Vision Center (CVC) participated in the #100tífiques programme, an initiative promoted by the Catalan Foundation for Research and Innovation (FCRI) and the Barcelona Institute for Science and Technology (BIST) in collaboration with the Education Department of the Generalitat of Catalonia.  The #100tífiques programme aims to raise awareness of the … Read more

February 11 is the “International Day of Women and Girls in Science” and also Grandmas in Science Day!

In collaboration with the Red Cross Cerdanyola-Ripollet-Montcada, our research center organized an activity for female senior citizens to celebrate the International Day of Women and Girls in Science, February 11. Twelve grandmas visited CVC and participated in a workshop aimed to encourage and empower them to get involved in science and enhance their natural curiosity … Read more

Postdoc junior (R2) position in Data Science

Reference: 20230215 About CVC The Computer Vision Center (CVC) is a non-profit research center established in 1995 by the Generalitat de Catalunya and the UniversitatAutònoma de Barcelona (UAB). Its mission is to carry out cutting-edge research that has the highest international impact in the field of computer vision. It also promotes the transference of knowledge … Read more

Wikimarathon – International Day of Women & Girls in Science

On the occasion of the International International Day of Women and Girls in Science (February 11), CVC is participating in a Wikimarathon coordinated by the Barcelona Biomedical Research Park (PRBB) together with ViquidonesUPF & Amical Wikimedia. We would like to invite you all to participate in this Wikimarathon. 🗓 February 13⏲ from 4:30 to 7:30 … Read more

CVC and the Red Cross celebrate Women in Science

International Day of Women and Girls in Science & also grandmas! CVC collaborates with Red Cross Cerdanyola-Ripollet-Montcada to bring senior women closer to science on the occasion of the International International Day of Women and Girls in Science. The event will take place on February 13. They will visit our facilities and experience AI and Computer Vision by … Read more

International Day of Women and Girls in Science

To promote full and equal access to and participation in science for women and to stimulate scientific vocations in girls, the United Nations General Assembly declared February 11th as the International Day of Women and Girls in Science. Long-standing biases and gender stereotypes are steering girls and women away from engineering and technology-related fields, and, … Read more

Deep learning based architectures for cross-domain image processing

Abstract: Human vision is restricted to the visual-optical spectrum. Machine vision is not. Cameras sensitive to diverse infrared spectral bands can improve the capacities of autonomous systems and provide a comprehensive view. Relevant scene content can be made visible, particularly in situations when sensors of other modalities, such as a visual-optical camera, require a source … Read more

Categories Phd

Mining large medical radiology image repositories

Abstract: Developing clinical predictive models by processing medical radiology images is often challenging due to high variability of data, noise and data scarcity. Using pre-trained feature extractors in deep learning configurations to initialise weights is often beneficial to the model optimisation process, leading to faster convergence and more accurate models. Although one can also benefit … Read more