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

CVC at Deep Learning Barcelona Symposium 2022

Once again CVC is participating in Deep Learning Barcelona Symposium (DLBCN) held at the UPC-Campus Nord, Barcelona, on 19 December. The event aims to showcase research on deep learning carried out by scientists in/from Barcelona (Scientists who currently work in Barcelona or who pursued part of their studies or career in Barcelona). This unique meeting gathers researchers … Read more

Improving generalization for classification and retrieval tasks

Abstract: In this talk we will present recent works that generally aim at improving the generalization of visual representations on both classification and retrieval tasks. We will start from a recent work on supervised pre-training and will present an approach that aims to improve the transferability of encoders learned in a supervised manner, while retaining … Read more

Deep Learning for Document, Scene and Satellite Images Processing and Recognition

Abstract: Deep learning applications have been thriving over the last decade in many different domains, including image processing and recognition. The driver for the vibrant development of deep learning have been the availability of abundant data. This talk reviews the main results of our research activities carried out over the last few years. During this … Read more

From scans to information: end-to-end information extraction from documents

Abstract: With the advancement of Transformers, especially as far as computer vision is concerned, we are starting to apply end-to-end neural networks, without OCR or other pre-/postprocessing techniques, to the challenges of document understanding and information extraction. I will present developments in this area and discuss potential problems from both theoretical (handling longer sequences) and … Read more

Five CVC scientists featured in the “Top 2% researchers in AI for 2021”

We are more than happy to announce that 5 of our #CVCPeople scientists were featured in the “Top 2% researchers in #AI for 2021″👉 September 2022 data-update for “Updated science-wide author databases of standardized citation indicators” – Elsevier BV (digitalcommonsdata.com). This ranking is created every year and makes publicly available a database of top-cited scientists providing standardized information on … Read more

Calibrated Fine-Grained Recognition and Retrieval

Abstract: In the last decade, many areas of computer vision have progressed to a level supporting reliable, and sometimes impressive, applications. I wil talk about two such domains, fine-grained recognition and visual retrieval. In the fine-grained recognition, I’ll discuss the issue of prior probability shift, classifier calibration and the choice of loss functions driven by … Read more

CVC women researchers included in the Special issue ‘Women in AI’ (MDPI journal)

The paper 📄 ‘Recognition of the Mental Workloads of Pilots in the Cockpit Using EEG Signals’, by our #CVCPeople Dr Aura Hernandez Sabaté and Dr Debora Gil (& José Yauri), was published in the ‘#WomeninAI‘ special issue, MDPI Open Access Journal. This issue features 17 research articles on the field of #AI that have a woman as the first author. Read the paper ➡️ https://www.mdpi.com/2076-3417/12/5/2298/htm

CIP 2022

After its eighth edition in Madrid back in 2019, the biennial celebration of the Iberian Conference on Perception (CIP) had to be postponed until this year due to the covid-19 pandemic. The ninth edition will be held from June 27 to June 29, in Barcelona, at Casa Convalescència. The venue, located in the historical complex of Hospital de la Santa Creu in Sant … Read more

Continual Learning from Pretrained Models

Abstract: Continual Learning (CL) is a paradigm where an agent learns over time from a stream of data. In this talk, we will discuss how to exploit pretrained models in CL. First, we will talk about “continual pretraining”, a scenario where a large pretrained model is updated over time. The results show that continual pretraining … Read more