Deep visual embedding for image classification

Adel Saleh, Mohamed Abdel-Nasser, Md Mostafa Kamal Sarker, Vivek Kumar Singh, Saddam Abdulwahab, Nasibeh Saffari, Miguel Angel Garcia, Domenec Puig

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

1 Citation (Scopus)

Abstract

This paper proposes a new visual embedding method for image classification. It goes further in the analogy with textual data and allows us to read visual sentences in a certain order as in the case of text. The proposed method considers the spatial relations between visual words. It uses a very popular text analysis method called 'word2vec'. In this method, we learn visual dictionaries based on filters of convolution layers of the convolutional neural network (CNN), which is used to capture the visual context of images. We employee visual embedding to convert words to real vectors. We evaluate many designs of dictionary building methods. To assess the performance of the proposed method, we used CIFAR10 and MNIST datasets. The experimental results show that the proposed visual embedding method outperforms the performance of several image classification methods. Experiments also show that our method can improve image classification regardless the structure of the CNN.

Original languageEnglish
Title of host publicationProceedings of 2018 International Conference on Innovative Trends in Computer Engineering (ITCE 2018)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages31-35
Number of pages5
ISBN (Electronic)9781538608807
DOIs
Publication statusPublished - May 2018
Event2018 International Conference on Innovative Trends in Computer Engineering, ITCE 2018 - Aswan, Egypt
Duration: 19 Feb 201821 Feb 2018

Publication series

NameProceedings of 2018 International Conference on Innovative Trends in Computer Engineering, ITCE 2018
Volume2018-March

Conference

Conference2018 International Conference on Innovative Trends in Computer Engineering, ITCE 2018
CountryEgypt
CityAswan
Period19/02/201821/02/2018

Keywords

  • Deep learning
  • Embedding
  • Image classification

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Signal Processing
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Deep visual embedding for image classification'. Together they form a unique fingerprint.

Cite this