Learning to rank salient segments extracted by multispectral Quantum Cuts
Author | Aytekin, Çağlar |
Author | Kiranyaz, Serkan |
Author | Gabbouj, Moncef |
Available date | 2021-04-15T10:49:02Z |
Publication Date | 2016 |
Publication Name | Pattern Recognition Letters |
Resource | Scopus |
ISSN | 1678655 |
Abstract | and third, multispectral approach is followed to generate multiple proposals instead of a single proposal as in Quantum Cuts. The proposed learn-to-rank algorithm is then applied to these multiple proposals in order to select the most appropriate one. Shape and appearance features are extracted from the proposed segments and regressed with respect to a given confidence measure resulting in a ranked list of proposals. This ranking yields consistent improvements in an extensive collection of benchmark datasets containing around 18k images. Our analysis on the random forest regression models that are trained on different datasets shows that, although these datasets are of quite different characteristics, a model trained in the most complex dataset consistently provides performance improvements in all the other datasets, hence yielding robust salient object segmentation with a significant performance gap compared to the competing methods. |
Language | en |
Publisher | Elsevier B.V. |
Subject | Learning to rank Multispectral analysis Quantum Cuts Saliency detection Salient object segmentation |
Type | Article |
Pagination | 91-99 |
Volume Number | 72 |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Electrical Engineering [2811 items ]