TY - GEN
T1 - Dropping Activations in Convolutional Neural Networks with Visual Attention Maps
AU - Obeso, Abraham Montoya
AU - Benois-Pineau, Jenny
AU - Vazquez, Mireya Sarai Garcia
AU - Acosta, Alejandro A.Ramirez
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - The introduction of visual attention models in data selection and features selection in CNNs for the task of image classification is an intensive and interesting research topic. In CNNs, the strategy of dropping activations, after features extraction layers, shown an increase in the generalization gap in large-scale datasets and avoiding over-fitting. Dropout has been studied in the literature in a fully-randomized manner to take down activations during training. In this paper, we introduce a saliency-based dropping strategy to take down activations in our AlexNet-like architecture. Our experiments are conducted for the specific task of specific Mexican architectural recognition, in 67 categories. The results are promising: The proposed approach outperformed other models reducing training time and reaching a higher accuracy.
AB - The introduction of visual attention models in data selection and features selection in CNNs for the task of image classification is an intensive and interesting research topic. In CNNs, the strategy of dropping activations, after features extraction layers, shown an increase in the generalization gap in large-scale datasets and avoiding over-fitting. Dropout has been studied in the literature in a fully-randomized manner to take down activations during training. In this paper, we introduce a saliency-based dropping strategy to take down activations in our AlexNet-like architecture. Our experiments are conducted for the specific task of specific Mexican architectural recognition, in 67 categories. The results are promising: The proposed approach outperformed other models reducing training time and reaching a higher accuracy.
KW - Cultural Heritage
KW - Deep Learning
KW - Dropping Activations
UR - http://www.scopus.com/inward/record.url?scp=85074347919&partnerID=8YFLogxK
U2 - 10.1109/CBMI.2019.8877380
DO - 10.1109/CBMI.2019.8877380
M3 - Contribución a la conferencia
AN - SCOPUS:85074347919
T3 - Proceedings - International Workshop on Content-Based Multimedia Indexing
BT - 2019 International Conference on Content-Based Multimedia Indexing, CBMI 2019 - Proceedings
PB - IEEE Computer Society
T2 - 17th International Conference on Content-Based Multimedia Indexing, CBMI 2019
Y2 - 4 September 2019 through 6 September 2019
ER -