Data efficient methods for plankton image classification

• Grant number: 20/15170-2
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: January 01, 2021
• End date: May 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Agreement: Belmont Forum
• Principal Investigator: Nina Sumiko Tomita Hirata
• Grantee: Antonio Jose Homsi Goulart
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 18/24167-5 - World Wide Web of Plankton Image Curation (WWW.PIC), AP.R

Abstract

The main goal of this postdoc project is to develop machine learning based computational methods to speed up both annotation and classification of plankton images, minimizing the required effort from the expert. The method should be able to effectively reuse previously generated knowledge, quickly producing new classifiers adapted to new imaging or use conditions. Unsupervised and semi-supervised machine learning approaches, possibly including user-interaction mechanisms, as well as techniques related to novelty detection and class imbalance treatment, are some of the research topics to be explored.

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

HOMSI GOULART, ANTONIO JOSE; MORIMITSU, ALEXANDRE; JACOMASSI, RENAN; HIRATA, NINA; LOPES, RUBENS; IEEE. Deep learning and t-SNE projection for plankton images clusterization. OCEANS 2021: SAN DIEGO - PORTO, v. N/A, p. 4-pg., 2021-01-01. (21/02902-8, 20/15170-2)