Mesh Saliency via Weakly Supervised Classification-for-Saliency CNN

Ran Song, YONGHUAI LIU, Paul Rosin

Research output: Contribution to journalArticle

132 Downloads (Pure)

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.
Original languageEnglish
JournalIEEE Transactions on Visualization and Computer Graphics
Early online date18 Jul 2019
DOIs
Publication statusE-pub ahead of print - 18 Jul 2019

Keywords

  • Mesh saliency
  • Deep learning
  • Transfer learning
  • weak supervision

Fingerprint Dive into the research topics of 'Mesh Saliency via Weakly Supervised Classification-for-Saliency CNN'. Together they form a unique fingerprint.

  • Cite this