Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining

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 takin...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transaction on neural networks and learning systems Ročník 27; číslo 6; s. 1163 - 1176
Hlavní autori: Zhang, Dingwen, Han, Junwei, Han, Jungong, Shao, Ling
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.06.2016
Predmet:
Construction
Cosaliency detection
Data mining
deep learning
Encoding
Feature extraction
Homogeneity
Image detection
Learning
Machine learning
Mining
Neural networks
Object recognition
prior transfer
Robustness
stacked denoising autoencoder (SDAE)
Training
Visualization
stacked denoising autoencoder (SDAE)
deep learning
Cosaliency detection
prior transfer
ISSN:2162-237X, 2162-2388, 2162-2388
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2015.2495161