Boosted convolutional neural networks
Research output: Contribution to conference › Paper › Research › peer-review
Standard
Boosted convolutional neural networks. / Moghimi, Mohammad; Saberian, Mohammad; Yang, Jian; Li, Li Jia; Vasconcelos, Nuno; Belongie, Serge.
2016. 24.1-24.13 Paper presented at 27th British Machine Vision Conference, BMVC 2016, York, United Kingdom.Research output: Contribution to conference › Paper › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - CONF
T1 - Boosted convolutional neural networks
AU - Moghimi, Mohammad
AU - Saberian, Mohammad
AU - Yang, Jian
AU - Li, Li Jia
AU - Vasconcelos, Nuno
AU - Belongie, Serge
N1 - Publisher Copyright: © 2016. The copyright of this document resides with its authors.
PY - 2016
Y1 - 2016
N2 - In this work, we propose a new algorithm for boosting Deep Convolutional Neural Networks (BoostCNN) to combine the merits of boosting and these networks. To learn this new model, we propose a novel algorithm to incorporate boosting weights into the deep learning architecture based on least square objective function. We also show that it is possible to use networks of different structures within the proposed boosting framework and BoostCNN is able to select the best network structure in each iteration. This not only results in superior performance but also reduces the required manual effort for finding the right network structure. Experiments show that the proposed method is able to achieve state-of-the-art performance on several fine-grained classification tasks such as bird, car, and aircraft classification.
AB - In this work, we propose a new algorithm for boosting Deep Convolutional Neural Networks (BoostCNN) to combine the merits of boosting and these networks. To learn this new model, we propose a novel algorithm to incorporate boosting weights into the deep learning architecture based on least square objective function. We also show that it is possible to use networks of different structures within the proposed boosting framework and BoostCNN is able to select the best network structure in each iteration. This not only results in superior performance but also reduces the required manual effort for finding the right network structure. Experiments show that the proposed method is able to achieve state-of-the-art performance on several fine-grained classification tasks such as bird, car, and aircraft classification.
UR - http://www.scopus.com/inward/record.url?scp=85047160033&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85047160033
SP - 24.1-24.13
T2 - 27th British Machine Vision Conference, BMVC 2016
Y2 - 19 September 2016 through 22 September 2016
ER -
ID: 301827868