New Methods for Learning Deep Visual Hierarchies

• Grant number: 13/11359-0
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: September 01, 2013
• End date: February 28, 2015
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Alexandre Xavier Falcão
• Grantee: Giovani Chiachia
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

While humans have an impressive ability in recognizing objects even under adverse observation conditions, computer vision is still constrained to the recognition of specific objects under controlled conditions. In order to reproduce human abilities, visual neuroscientists have long been uncovering important information about the underlying mechanisms that brain may use to perform visual tasks. Nowadays, the use of feedforward visual hierarchies consisting of many layers of linear and nonlinear biologically-inspired operations has shown to give computers an outstanding ability in recognizing faces, animals, vehicles, and a number of other objects. An interesting property of these hierarchies is that they operate directly in the image domain, and that, with simple operations, they are able to learn image processing steps that would instead have to be manually engineered in traditional computer vision approaches. In spite of the recent results, many questions remain about how to learn deep visual hierarchies. Its architecture, for example, was found to be especially relevant. Another relevant aspect is how to train the hierarchy so that it can effectively learn to extract meaningful information from images. In this project, we propose reasonable directions to advance on these aspects. We believe that we have means to address these directions -- presenting preliminary results for one of them -- and that their accomplishment will enable us to achieve new levels of performance in difficult computer vision problems such as unconstrained face recognition, object recognition in general, and content-based image retrieval, among others.

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BONDI, L.; BAROFFIO, L.; CESANA, M.; TAGLIASACCHI, M.; CHIACHIA, G.; ROCHA, A.. Rate-energy-accuracy optimization of convolutional architectures for face recognition. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v. 36, p. 142-148, APR 2016. (13/11359-0)

RUPPERT, GUILHERME C. S.; CHIACHIA, GIOVANI; BERGO, FELIPE P. G.; FAVRETTO, FERNANDA O.; YASUDA, CLARISSA L.; ROCHA, ANDERSON; FALCAO, ALEXANDRE X.. Medical image registration based on watershed transform from greyscale marker and multi-scale parameter search. COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION, v. 5, n. 2, p. 138-156, 2017. (13/11359-0, 07/52015-0, 10/00994-8, 10/05647-4)

MENOTTI, DAVID; CHIACHIA, GIOVANI; PINTO, ALLAN; SCHWARTZ, WILLIAM ROBSON; PEDRINI, HELIO; FALCAO, ALEXANDRE XAVIER; ROCHA, ANDERSON. Deep Representations for Iris, Face, and Fingerprint Spoofing Detection. IEEE Transactions on Information Forensics and Security, v. 10, n. 4, p. 864-879, APR 2015. (11/22749-8, 13/04172-0, 13/11359-0, 10/05647-4)

CHIACHIA, GIOVANI; FALCAO, ALEXANDRE X.; PINTO, NICOLAS; ROCHA, ANDERSON; COX, DAVID. Learning Person-Specific Representations From Faces in the Wild. IEEE Transactions on Information Forensics and Security, v. 9, n. 12, p. 2089-2099, DEC 2014. (13/11359-0, 10/00994-8, 10/05647-4)