Advanced search
Start date
Betweenand

Understanding the role of shortcuts and distribution shifts in deep learning generalization

Grant number: 22/09606-8
Support Opportunities:Scholarships abroad - Research Internship - Doctorate
Effective date (Start): October 27, 2022
Effective date (End): April 26, 2023
Field of knowledge:Physical Sciences and Mathematics - Computer Science
Principal Investigator:Sandra Eliza Fontes de Avila
Grantee:Alceu Emanuel Bissoto
Supervisor: Ana Catarina Fidalgo Barata
Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
Research place: Universidade de Lisboa, Portugal  
Associated to the scholarship:19/19619-7 - Generating unlimited skin lesion images with generative adversarial networks, BP.DR

Abstract

Deep learning achieved amazing success in computer vision, and natural language processing. Spurious correlations (biases) in data are able to poison models, causing lack of generalization to out-of-distribution data, which is an obstacle for the application of deep learning to real-world problems as medical imaging. Despite the existence of robust learning algorithms, their performance highly depends on hyperparameter selection, and on the characteristics of the data and its biases. Also, solutions are still dependent on the annotation of spurious sources, and the phenomenons surrounding out-of-distribution generalization is still not near to be understood. Also, despite years of research on domain generalization, evaluation of robust solutions only show minor improvements over consolidated baselines. In this scenario, we study the interaction between two important phenomenons: shortcut learning and domain shift. Shortcuts appear as spurious correlations on training data, and domain shift appears as out-of-distribution test sets. We think that by understanding how base and robust models are affected by these phenomenons, we can design better generalization evaluation methods, debiasing techniques, and better understand the learning mechanism in deep neural networks. (AU)

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

Please report errors in scientific publications list using this form.