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

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.

Citation

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: https://doi.org/10.1109/ITCE.2018.8316596

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2018 international conference on Innovative trends in computer engineering (ITCE 2018)
• 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: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Pages: 31-35
• ISBN: 9781538608777
• DOI: https://doi.org/10.1109/ITCE.2018.8316596
• Keywords: Deep learning; Embedding; Image classification
• Public URL: https://rgu-repository.worktribe.com/output/1542133