Skip to main content

Research Repository

Advanced Search

Deep visual embedding for image classification.

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


Adel Saleh

Mohamed Abdel-Nasser

Vivek Kumar Singh

Saddam Abdulwahab

Nasibeh Saffari

Miguel Angel Garcia

Domenec Puig


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.


SALEH, A., ABDEL-NASSER, M., SARKER, M.M.K., SINGH, V.K., ABDULWAHAB, S., SAFFARI, N., GARCIA, M.A. and PUIG, D. 2018. Deep visual embedding for image classification. In Proceedings of 2018 international conference on Innovative trends in computer engineering (ITCE 2018), 19-21 February 2018, Aswan, Egypt. Piscataway: IEEE [online], pages 31-35. Available from:

Conference Name 2018 international conference on Innovative trends in computer engineering (ITCE 2018)
Conference Location Aswan, Egypt
Start Date Feb 19, 2018
End Date Feb 21, 2018
Acceptance Date Nov 15, 2017
Online Publication Date Feb 21, 2018
Publication Date Mar 15, 2018
Deposit Date Dec 4, 2021
Publicly Available Date Jan 18, 2022
Publisher IEEE Institute of Electrical and Electronics Engineers
Pages 31-35
ISBN 9781538608777
Keywords Deep learning; Embedding; Image classification
Public URL


You might also like

Downloadable Citations