Incorporating multiple distance spaces in optimum-path forest classification to improve feedback-based learning

Silva, Andre Tavares da; Santos, Jefersson A. dos; Falcão, Alexandre X.; Torres, Ricardo da S.; Magalhães, Leo Pini

doi:10.1016/j.cviu.2011.12.001

Cited by 18 publications

(13 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use genetic programming (GP) for learning reference similarity functions and the Optimum-Path Forest (OPF) classifier for labeling references. The combination of OPF and GP has been very effective in relevance feedback approaches [32], yielding better results than methods based on using only GP-based similarity functions.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Those initiatives, however, focus on content-based image retrieval [32,33] and classification [34] tasks. In the approaches presented in [32,34], GP is also used to determine edge weights in OPF graphs. Those RF methods, however, adopt a binary classification model in which each image is classified as either relevant or non-relevant.…”

Section: Relevance Feedbackmentioning

confidence: 99%

“…Relevance feedback (RF) approaches have been proposed based on the OPF classifier [32][33][34]. Those initiatives, however, focus on content-based image retrieval [32,33] and classification [34] tasks.…”

Section: Relevance Feedbackmentioning

confidence: 99%

“…We simulate the presence of ideal users providing feedback, a typical strategy used to evaluate relevance feedback systems [32][33][34]. In our case, ideal users always assign ambiguous references to the correct author at each iteration.…”

Section: Experimental Protocolmentioning

confidence: 99%

See 3 more Smart Citations

A relevance feedback approach for the author name disambiguation problem

Godoi

Torres

Carvalho

et al. 2013

Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries

Self Cite

View full text Add to dashboard Cite

This paper presents a new name disambiguation method that exploits user feedback on ambiguous references across iterations. An unsupervised step is used to define pure training samples, and a hybrid supervised step is employed to learn a classification model for assigning references to authors. Our classification scheme combines the OptimumPath Forest (OPF) classifier with complex reference similarity functions generated by a Genetic Programming framework. Experiments demonstrate that the proposed method yields better results than state-of-the-art disambiguation methods on two traditional datasets.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Relevance Feedbackmentioning

confidence: 99%

Section: Relevance Feedbackmentioning

confidence: 99%

Section: Experimental Protocolmentioning

confidence: 99%

See 2 more Smart Citations

A relevance feedback approach for the author name disambiguation problem

Godoi

Torres

Carvalho

et al. 2013

Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries

Self Cite

View full text Add to dashboard Cite

show abstract

“…In both works, the use of swarmbased optimization techniques is motivated by their simplicity and elegance to solve such sort of optimization problems. An interesting work has been done by Silva et al [35], which employed a similar idea, but in the context of CBIR task.…”

Section: Introductionmentioning

confidence: 99%

Swarm-based Descriptor Combination and its Application for Image Classification

Mansano¹,

Matsuoka²,

Abiuzzi³

et al. 2014

ELCVIA

View full text Add to dashboard Cite

In this paper, we deal with the descriptor combination problem in image classification tasks. This problem refers to the definition of an appropriate combination of image content descriptors that characterize different visual properties, such as color, shape and texture. In this paper, we propose to model the descriptor combination as a swarm-based optimization problem, which finds out the set of parameters that maximizes the classification accuracy of the Optimum-Path Forest (OPF) classifier. In our model, a descriptor is seen as a pair composed of a feature extraction algorithm and a suitable distance function. Our strategy here is to combine distance scores defined by different descriptors, as well as to employ them to weight OPF edges, which connect samples in the feature space. An extensive evaluation of several swarm-based optimization techniques was performed. Experimental results have demonstrated the robustness of the proposed combination approach.

show abstract