Semiconducting bilinear deep learning for incomplete image recognition

Sheng Hua Zhong, Yan Liu, Fu Lai Korris Chung, Gangshan Wu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

5 Citations (Scopus)

Abstract

Image recognition with incomplete data is a well-known hard problem in multimedia content analysis. This paper proposes a novel deep learning technique called semiconducting bilinear deep belief networks (SBDBN) by referencing human's visual cortex and intelligent perception. Inheriting from deep models, SBDBN simulates the laminar structure of human's cerebral cortex and the neural loop in human's visual areas. To address the special difficulties of image recognition with incomplete data, we design a novel second-order deep architecture with semiconducting restricted boltzmann machines. Moreover, two peaks activation of human's perception is implemented by three learning stages of semiconducting bilinear discriminant initialization, greedy layer-wise reconstruction, and global finetuning. Owing to exploiting the embedding information according to the reliable features rather than any completion of missing features, the proposed SBDBN has demonstrated outstanding recognition ability on two standard datasets and one constructed dataset, comparing with both incomplete image recognition techniques and existing deep learning models.
Original languageEnglish
Title of host publicationProceedings of the 2nd ACM International Conference on Multimedia Retrieval, ICMR 2012
DOIs
Publication statusPublished - 27 Jul 2012
Event2nd ACM International Conference on Multimedia Retrieval, ICMR 2012 - Hong Kong, Hong Kong
Duration: 5 Jun 20128 Jun 2012

Conference

Conference2nd ACM International Conference on Multimedia Retrieval, ICMR 2012
CountryHong Kong
CityHong Kong
Period5/06/128/06/12

Keywords

  • Deep learning
  • Image recognition
  • Missing features
  • Semiconducting bilinear discriminant initialization
  • Semiconducting RBM

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Cite this