Integrating deep features for material recognition

Yan Zhang, Mete Ozay, Xing Liu, Takayuki Okatani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

This paper considers the problem of material recognition. Motivated by observation of close interconnections between material and object recognition, we study how to select and integrate multiple features obtained by different models of Convolutional Neural Networks (CNNs) trained in a transfer learning setting. To be specific, we first compute activations of features using representations on images to select a set of samples which are best represented by the features. Then, we measure uncertainty of the features by computing entropy of class distributions for each sample set. Finally, we compute contribution of each feature to representation of classes for feature selection and integration. Experimental results show that the proposed method achieves state-of-the-art performance on two benchmark datasets for material recognition. Additionally, we introduce a new material dataset, named EFMD, which extends Flickr Material Database (FMD). By the employment of the EFMD for transfer learning, we achieve 84.0% ± 1.8% accuracy on the FMD dataset, which is close to the reported human performance 84.9%.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3697-3702
Number of pages6
ISBN (Electronic)9781509048472
DOIs
Publication statusPublished - 2016 Jan 1
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: 2016 Dec 42016 Dec 8

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume0
ISSN (Print)1051-4651

Other

Other23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period16/12/416/12/8

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Integrating deep features for material recognition'. Together they form a unique fingerprint.

Cite this