Mesh saliency via weakly supervised classification-for-saliency CNN

Song, Ran, Liu, Yonghuai and Rosin, Paul ORCID: https://orcid.org/0000-0002-4965-3884 2021. Mesh saliency via weakly supervised classification-for-saliency CNN. IEEE Transactions on Visualization and Computer Graphics 27 (1) , pp. 151-164. 10.1109/TVCG.2019.2928794

Preview

PDF - Accepted Post-Print Version Download (24MB) | Preview

Abstract

Recently, effort has been made to apply deep learning to the detection of mesh saliency. However, one major barrier is to collect a large amount of vertex-level annotation as saliency ground truth for training the neural networks. Quite a few pilot studies showed that this task is quite difficult. In this work, we solve this problem by developing a novel network trained in a weakly supervised manner. The training is end-to-end and does not require any saliency ground truth but only the class membership of meshes. Our Classification-for-Saliency CNN (CfS-CNN) employs a multi-view setup and contains a newly designed two-channel structure which integrates view-based features of both classification and saliency. It essentially transfers knowledge from 3D object classification to mesh saliency. Our approach significantly outperforms the existing state-of-the-art methods according to extensive experimental results. Also, the CfS-CNN can be directly used for scene saliency. We showcase two novel applications based on scene saliency to demonstrate its utility.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers (IEEE)
ISSN:	1077-2626
Date of First Compliant Deposit:	15 August 2019
Date of Acceptance:	10 July 2019
Last Modified:	18 Nov 2024 07:00
URI:	https://orca.cardiff.ac.uk/id/eprint/124144

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item