A Dilated Inception Network for Visual Saliency Prediction

04/07/2019
by   Sheng Yang, et al.
0

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 proposed 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 probability distribution prediction task for global saliency inference instead of a typical 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.

READ FULL TEXT

page 1

page 4

page 9

page 12

research
04/05/2018

End-to-End Saliency Mapping via Probability Distribution Prediction

Most saliency estimation methods aim to explicitly model low-level consp...
research
01/01/2022

SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images

This paper introduces a new framework to predict visual attention of omn...
research
05/07/2017

Deep Visual Attention Prediction

Deep Convolutional Neural Networks (CNNs) have made substantial improvem...
research
01/12/2018

Deep saliency: What is learnt by a deep network about saliency?

Deep convolutional neural networks have achieved impressive performance ...
research
08/31/2020

RecSal : Deep Recursive Supervision for Visual Saliency Prediction

State-of-the-art saliency prediction methods develop upon model architec...
research
01/19/2018

A Foreground Inference Network for Video Surveillance Using Multi-View Receptive Field

Foreground (FG) pixel labelling plays a vital role in video surveillance...
research
02/04/2023

GDB: Gated convolutions-based Document Binarization

Document binarization is a key pre-processing step for many document ana...

Please sign up or login with your details

Forgot password? Click here to reset