Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning

Preprint English OPEN
Castro, Daniel C.; Tan, Jeremy; Kainz, Bernhard; Konukoglu, Ender; Glocker, Ben;
(2018)
  • Subject: Statistics - Machine Learning | Computer Science - Machine Learning

Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery. However, a major cha... View more
  • References (31)
    31 references, page 1 of 4

    Arora, S., Risteski, A., and Zhang, Y. (2018). Do GANs learn the distribution? Some theory and empirics. In International Conference on Learning Representations (ICLR 2018).

    Aubry, M., Maturana, D., Efros, A. A., Russell, B. C., and Sivic, J. (2014). Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), pages 3762-3769. IEEE. Dataset URL https://www.di.ens.fr/willow/research/seeing3Dchairs/.

    Bin´kowski, M., Sutherland, D., Arbel, M., and Gretton, A. (2018). Demystifying MMD GANs. In International Conference on Learning Representations (ICLR 2018). arXiv:1801.01401v1.

    Bounliphone, W., Belilovsky, E., Blaschko, M. B., Antonoglou, I., and Gretton, A. (2016). A test of relative similarity for model selection in generative models. In International Conference on Learning Representations (ICLR 2016). arXiv:1511.04581.

    Bulatov, Y. (2011). notMNIST dataset. URL https://yaroslavvb.blogspot.co.uk/ 2011/09/notmnist-dataset.html. [Accessed on: 2018-05-08].

    Chen, T. Q., Li, X., Grosse, R., and Duvenaud, D. (2018). Isolating sources of disentanglement in variational autoencoders. In International Conference on Learning Representations Workshop (ICLR 2018). arXiv:1802.04942.

    Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016). InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets. In Advances in Neural Information Processing Systems 29 (NIPS 2016), pages 2172-2180.

    Cohen, G., Afshar, S., Tapson, J., and van Schaik, A. (2017). EMNIST: an extension of MNIST to handwritten letters, arXiv:1702.05373. Dataset URL https://www.nist.gov/itl/iad/ image-group/emnist-dataset.

    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Advances in Neural Information Processing Systems 27 (NIPS 2014), pages 2672-2680.

    Gretton, A., Borgwardt, K. M., Rasch, M. J., Schölkopf, B., and Smola, A. J. (2012). A kernel two-sample test. Journal of Machine Learning Research, 13(Mar):723-773.

  • Related Research Results (1)
  • Related Organizations (1)
  • Metrics
Share - Bookmark