Advanced search
Start date

Self-supervised learning for biometrics and beyond

Grant number: 22/02299-2
Support Opportunities:Scholarships abroad - Research Internship - Doctorate (Direct)
Effective date (Start): July 01, 2022
Effective date (End): June 30, 2023
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal Investigator:Anderson de Rezende Rocha
Grantee:Gabriel Capiteli Bertocco
Supervisor: Terrance E. Boult
Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
Research place: University of Colorado, Colorado Springs (UCCS), United States  
Associated to the scholarship:19/15825-1 - Mining persons, objects and places of interest from heterogeneous data sources, BP.DD


A fundamental problem in machine learning is dealing with unlabeled data. Most models rely on massive labeled data to achieve state-of-art results. However, data labeling is a time-consuming, costly, biased- and error-prone task. It is paramount to develop models that can mine patterns in a fully-unsupervised scenario allowing a fast and bias-free deployment. This project aims at devising self-supervised learning algorithms to deal with unlabeled data for generic label-absent scenarios with challenging setups. A challenging setup might contain high intra-class disparity (features from the same class are far away from each other) and high inter-class similarity (features from different classes might be closer). To instantiate this complex requirement, we explore the Long-range Semi-supervised and Unsupervised Re-Identification of people problem, where images of people are captured from different distances and moments in time, resulting in changes in resolution and appearance. The solution can be extended to objects and places, and used for a range of social impact applications, such as investigations and event understanding. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items

Please report errors in scientific publications list by writing to: