Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Supervised and unsupervised relevance sampling in handcrafted and deep learning features obtained from image collections

Full text
Author(s):
Ponti, Moacir A. [1] ; da Costa, Gabriel B. Paranhos [1] ; Santos, Fernando P. [1] ; Silveira, Kaue U. [1]
Total Authors: 4
Affiliation:
[1] Univ Sao Paulo, ICMC, BR-13566590 Sao Carlos, SP - Brazil
Total Affiliations: 1
Document type: Journal article
Source: APPLIED SOFT COMPUTING; v. 80, p. 414-424, JUL 2019.
Web of Science Citations: 0
Abstract

Image collections are currently widely available and are being generated in a fast pace due to mobile and accessible equipment. In principle, that is a good scenario taking into account the design of successful visual pattern recognition systems. However, in particular for classification tasks, one may need to choose which examples are more relevant in order to build a training set that well represents the data, since they often require representative and sufficient observations to be accurate. In this paper we investigated three methods for selecting relevant examples from image collections based on learning models from small portions of the available data. We considered supervised methods that need labels to allow selection, and an unsupervised method that is agnostic to labels. The image datasets studied were described using both handcrafted and deep learning features. A general purpose algorithm is proposed which uses learning methods as subroutines. We show that our relevance selection algorithm outperforms random selection, in particular when using unlabelled data in an unsupervised approach, significantly reducing the size of the training set with little decrease in the test accuracy. (AU)

FAPESP's process: 16/16111-4 - Feature learning applied to sketch-based image retrieval and low-altitude remote sensing
Grantee:Moacir Antonelli Ponti
Support type: Regular Research Grants
FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
Grantee:José Alberto Cuminato
Support type: Research Grants - Research, Innovation and Dissemination Centers - RIDC
FAPESP's process: 15/05310-3 - Representation Learning of spatio-temporal features from video
Grantee:Gabriel de Barros Paranhos da Costa
Support type: Scholarships in Brazil - Doctorate