Visual analytics for user-assisted label propagation in neural-network image classifier design

• Grant number: 17/25327-3
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: April 01, 2018
• End date: September 30, 2018
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Alexandre Xavier Falcão
• Grantee: Bárbara Caroline Benato
• Supervisor: Alexandru-Cristian Telea
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Institution abroad: University of Groningen, Netherlands
• Associated to the scholarship: 16/25776-0 - Autoencoders neural networks optimization by visual analytics data, BP.MS

Abstract

Deep neural networks can be very effective for image classification, but they usually rely on regularization methods, transfer learning, and/or large supervised training sets to reduce/avoid high classification accuracy on the training data with low accuracy on unseen test sets --- i.e., a phenomenon known as data overfitting. Transfer learning is not always possible and large supervised training sets are usually impractical in applications that require experts for data supervision. Possible solutions include data augmentation and other strategies to improve the architecture and weights of the network from a limited number of supervised examples. We have investigated such solutions in the main project, FAPESP 2016/25776-0, through the use of Encoder-Decoder Neural Networks (EDNNs), Convolutional Neural Networks (CNNs), and Visual Analytics. We are interested in solutions that improve the design of a CNN for image classification by exploiting the EDNN and Visual Analytics methods to copy with the absence of supervised examples. Therefore, the purpose of this BEPE project is the design of an user interface for interactive machine learning based on EDNNs, CNNs, and Visual Analytics. Validation studies will be conducted with image datasets from distinct applications related to the thematic project, FAPESP 2014/12236-1, coordinated by the advisor.

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.)

BENATO, BARBARA C.; GOMES, JANCARLO F.; TELEA, ALEXANDRU C.; FALCAO, ALEXANDRE X.. Semi-automatic data annotation guided by feature space projection. PATTERN RECOGNITION, v. 109, JAN 2021. (16/25776-0, 14/12236-1, 17/25327-3)

BENATO, BARBARA C.; TELEA, ALEXANDRU C.; FALCAO, ALEXANDRE X.; IEEE. Semi-Supervised Learning with Interactive Label Propagation guided by Feature Space Projections. PROCEEDINGS 2018 31ST SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), v. N/A, p. 8-pg., 2018-01-01. (16/25776-0, 14/12236-1, 17/25327-3)