Please use this identifier to cite or link to this item:
|Title:||Nearest Neighbors Distance Ratio Open-set Classifier|
Nearest neighbors distance ratio open-set classifier
|Author:||Mendes Junior, Pedro R.|
Souza, Roberto M. de
Weneck, Rafael de O.
Stein, Bernardo V.
Pazinato, Daniel V.
Almeida, Waldir R. de
Penatti, Otávio A. B.
Torres, Ricardo da S.
|Abstract:||In this paper, we propose a novel multiclass classifier for the open-set recognition scenario. This scenario is the one in which there are no a priori training samples for some classes that might appear during testing. Usually, many applications are inherently open set. Consequently, successful closed-set solutions in the literature are not always suitable for real-world recognition problems. The proposed open-set classifier extends upon the Nearest-Neighbor (NN) classifier. Nearest neighbors are simple, parameter independent, multiclass, and widely used for closed-set problems. The proposed Open-Set NN (OSNN) method incorporates the ability of recognizing samples belonging to classes that are unknown at training time, being suitable for open-set recognition. In addition, we explore evaluation measures for open-set problems, properly measuring the resilience of methods to unknown classes during testing. For validation, we consider large freely-available benchmarks with different open-set recognition regimes and demonstrate that the proposed OSNN significantly outperforms their counterparts in the literature.|
In this paper, we propose a novel multiclass classifier for the open-set recognition scenario. This scenario is the one in which there are no a priori training samples for some classes that might appear during testing. Usually, many applications are inher
Nearest Neighbor Classifier
Open-set Nearest-neighbor Classifier
Nearest Neighbors Distance Ratio
Open-set Evaluation Measures
Reconhecimento em cenário aberto
Reconhecimento de padrões
|Citation:||Machine Learning. Springer, v. 106, p. 359 - 386, 2017.|
|Appears in Collections:||IC - Artigos e Outros Documentos|
FEA - Artigos e Outros Documentos
FEEC - Artigos e Outros Documentos
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.