Contextual encoder–decoder network for visual saliency prediction

Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted and augmented with contextual information. However, existin...

Full description

Saved in:
Bibliographic Details
Published in:Neural networks Vol. 129; pp. 261 - 270
Main Authors: Kroner, Alexander, Senden, Mario, Driessens, Kurt, Goebel, Rainer
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.09.2020
Subjects:
Computer vision
Convolutional neural networks
Deep learning
Human fixations
Saliency prediction
Deep learning
Computer vision
Saliency prediction
Human fixations
Convolutional neural networks
ISSN:0893-6080, 1879-2782, 1879-2782
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted and augmented with contextual information. However, existing models aimed at explaining human fixation maps do not incorporate such a mechanism explicitly. Here we propose an approach based on a convolutional neural network pre-trained on a large-scale image classification task. The architecture forms an encoder–decoder structure and includes a module with multiple convolutional layers at different dilation rates to capture multi-scale features in parallel. Moreover, we combine the resulting representations with global scene information for accurately predicting visual saliency. Our model achieves competitive and consistent results across multiple evaluation metrics on two public saliency benchmarks and we demonstrate the effectiveness of the suggested approach on five datasets and selected examples. Compared to state of the art approaches, the network is based on a lightweight image classification backbone and hence presents a suitable choice for applications with limited computational resources, such as (virtual) robotic systems, to estimate human fixations across complex natural scenes. Our TensorFlow implementation is openly available at https://github.com/alexanderkroner/saliency.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
1879-2782
DOI:10.1016/j.neunet.2020.05.004