Issue |
MATEC Web Conf.
Volume 309, 2020
2019 International Conference on Computer Science Communication and Network Security (CSCNS2019)
|
|
---|---|---|
Article Number | 03028 | |
Number of page(s) | 8 | |
Section | Smart Algorithms and Recognition | |
DOI | https://doi.org/10.1051/matecconf/202030903028 | |
Published online | 04 March 2020 |
Multi-scale fusion and non-local attention mechanism based salient object detection
Zhejiang Normal University, Jinhua, Zhejiang, China
* Corresponding author: 479059697@qq.com
With the development of deep learning, researches in the field of computer vision are attracting more attention. As the pre-processing operation of visual tasks, a salient model may focus on pure architectures. The paper proposes a new multi-scale fusion network to enrich high-level redundant information with the enlarged receptive field. With the guidance of attention mechanism, the framework can capture more effective correlation spatial and channels information. Building a short-connection between high-level and each level features to transmit the contextual features. The model can be used in a variety of complex scenes for end-to- end image detection, with simple structure and strong versatility. Experimental results obtained on multiple common datasets have shown that the proposed model achieved better performance both in the visual effect and the accuracy for small object and multi-target detection.
Key words: Salient object detection / Multi-scale fusion / Guidance
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.