TY - GEN
T1 - Deep visual embedding for image classification
AU - Saleh, Adel
AU - Abdel-Nasser, Mohamed
AU - Sarker, Md Mostafa Kamal
AU - Singh, Vivek Kumar
AU - Abdulwahab, Saddam
AU - Saffari, Nasibeh
AU - Garcia, Miguel Angel
AU - Puig, Domenec
PY - 2018/5
Y1 - 2018/5
N2 - 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.
AB - 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.
KW - Deep learning
KW - Embedding
KW - Image classification
U2 - 10.1109/ITCE.2018.8316596
DO - 10.1109/ITCE.2018.8316596
M3 - Conference contribution
AN - SCOPUS:85047429101
T3 - Proceedings of 2018 International Conference on Innovative Trends in Computer Engineering, ITCE 2018
SP - 31
EP - 35
BT - Proceedings of 2018 International Conference on Innovative Trends in Computer Engineering (ITCE 2018)
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 International Conference on Innovative Trends in Computer Engineering, ITCE 2018
Y2 - 19 February 2018 through 21 February 2018
ER -