Home > Research > Publications & Outputs > Cosaliency Detection Based on Intrasaliency Pri...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
Close
<mark>Journal publication date</mark>06/2016
<mark>Journal</mark>IEEE Transactions on Neural Networks
Issue number6
Volume27
Number of pages14
Pages (from-to)1163-1176
Publication StatusPublished
Early online date11/11/15
<mark>Original language</mark>English

Abstract

As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images. It differs from the conventional saliency detection paradigm in which saliency detection for each image is determined one by one independently without taking advantage of the homogeneity in the data pool of multiple related images. In this paper, we propose a novel cosaliency detection approach using deep learning models. Two new concepts, called intrasaliency prior transfer and deep intersaliency mining, are introduced and explored in the proposed work. For the intrasaliency prior transfer, we build a stacked denoising autoencoder (SDAE) to learn the saliency prior knowledge from auxiliary annotated data sets and then transfer the learned knowledge to estimate the intrasaliency for each image in cosaliency data sets. For the deep intersaliency mining, we formulate it by using the deep reconstruction residual obtained in the highest hidden layer of a self-trained SDAE. The obtained deep intersaliency can extract more intrinsic and general hidden patterns to discover the homogeneity of cosalient objects in terms of some higher level concepts. Finally, the cosaliency maps are generated by weighted integration of the proposed intrasaliency prior, deep intersaliency, and traditional shallow intersaliency. Comprehensive experiments over diverse publicly available benchmark data sets demonstrate consistent performance gains of the proposed method over the state-of-the-art cosaliency detection methods.