Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/143872
Title: A dilated inception network for visual saliency prediction
Authors: Yang, Sheng
Lin, Guosheng
Jiang, Qiuping
Lin, Weisi
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Yang, S., Lin, G., Jiang, Q., & Lin, W. (2020). A dilated inception network for visual saliency prediction. IEEE Transactions on Multimedia, 22(8), 2163-2176. doi:10.1109/TMM.2019.2947352
Journal: IEEE Transactions on Multimedia
Abstract: Recently, with the advent of deep convolutional neural networks (DCNN), the improvements in visual saliency prediction research are impressive. One possible direction to approach the next improvement is to fully characterize the multi-scale saliency-influential factors with a computationally-friendly module in DCNN architectures. In this work, we propose an end-to-end dilated inception network (DINet) for visual saliency prediction. It captures multi-scale contextual features effectively with very limited extra parameters. Instead of utilizing parallel standard convolutions with different kernel sizes as the existing inception module, our proposed dilated inception module (DIM) uses parallel dilated convolutions with different dilation rates which can significantly reduce the computation load while enriching the diversity of receptive fields in feature maps. Moreover, the performance of our saliency model is further improved by using a set of linear normalization-based probability distribution distance metrics as loss functions. As such, we can formulate saliency prediction as a global probability distribution prediction task for better saliency inference instead of a pixel-wise regression problem. Experimental results on several challenging saliency benchmark datasets demonstrate that our DINet with proposed loss functions can achieve state-of-the-art performance with shorter inference time.
URI: https://hdl.handle.net/10356/143872
ISSN: 1520-9210
DOI: 10.1109/TMM.2019.2947352
DOI (Related Dataset): https://doi.org/10.21979/N9/OIYLBK
Rights: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TMM.2019.2947352
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
A Dilated Inception Network for Visual Saliency Prediction.pdf4.53 MBAdobe PDFView/Open

PublonsTM
Citations

6
Updated on Jan 14, 2021

Page view(s)

21
Updated on Jan 20, 2021

Download(s)

8
Updated on Jan 20, 2021

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.