Marginalized CNN: Learning Deep Invariant Representations

Jian ZHAO, Jianshu Li, Fang Zhao, Xuecheng Nie, Yunpeng Chen, Shuicheng Yan and Jiashi Feng

Abstract

Training a deep neural network usually requires sufficient annotated samples. The scarcity of supervision samples in practice thus becomes the major bottleneck on performance of the network. In this work, we propose a principled method to circumvent this difficulty through marginalizing all the possible transformations over samples, termed as marginalized Convolutional Neural Network (mCNN). mCNN implicitly considers infinitely many transformed copies of the training data in every training epoch and therefore is able to learn representations invariant for transformation in an end-to-end way. We prove that such marginalization can be understood as a classic CNN with a special form of regularization and thus is efficient for implementation and not restricted to the CNN module used. Experimental results on the MNIST and affNIST digit number datasets demonstrate that mCNN can match or outperform the original CNN with much fewer training samples. Besides, mCNN also performs well for face recognition on the recently released large-scale MS-Cele-1M dataset and outperforms state-of-the-arts.

Session

Posters

Files

PDF iconPaper (PDF)
PDF iconSupplementary (PDF)

DOI

10.5244/C.31.127
https://dx.doi.org/10.5244/C.31.127

Citation

Jian ZHAO, Jianshu Li, Fang Zhao, Xuecheng Nie, Yunpeng Chen, Shuicheng Yan and Jiashi Feng. Marginalized CNN: Learning Deep Invariant Representations. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 127.1-127.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_127,
                title={Marginalized CNN: Learning Deep Invariant Representations},
                author={Jian ZHAO, Jianshu Li, Fang Zhao, Xuecheng Nie, Yunpeng Chen, Shuicheng Yan and Jiashi Feng},
                year={2017},
                month={September},
                pages={127.1-127.12},
                articleno={127},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.127},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.127}
            }