Numerosity Representation in InfoGAN: An Empirical Study
Andrea Zanetti , Alberto Testolin , Marco Zorzi , Paweł Wawrzyński
AbstractIt has been shown that “visual numerosity emerges as a statistical property of images in ‘deep networks’ that learn a hierarchical generative model of the sensory input”, through unsupervised deep learning . The original deep generative model was based on stochastic neurons and, more importantly, on input (image) reconstruction. Statistical analysis highlighted a correlation between the numerosity present in the input and the population activity of some neurons in the second hidden layer of the network, whereas population activity of neurons in the first hidden layer correlated with total area (i.e., number of pixels) of the objects in the image. Here we further investigate whether numerosity information can be isolated as a disentangled factor of variation of the visual input. We train in unsupervised and semi-supervised fashion a latent-space generative model that has been shown capable of disentangling relevant semantic features in a variety of complex datasets, and we test its generative performance under different conditions. We then propose an approach to the problem based on the assumption that, in order to let numerosity emerge as disentangled factor of variation, we need to cancel out the sources of variation at graphical level.
|Publication size in sheets||0.55|
|Book||Rojas Ignacio, Joya Gonzalo, Catala Andreu: Advances inComputationalIntelligence15th International Work-Conferenceon Artificial Neural Networks, IWANN 2019, Lecture Notes In Computer Science, vol. II, 2019, Springer, ISBN 978-3-030-20520-1, [978-3-030-20521-8 (eBook)], 940 p.|
|Score||= 70.0, 10-01-2020, ChapterFromConference|
|Publication indicators||= 0; = 0|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.