Variational Autoencoder for Deep Learning of Images, Labels and Captions

A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to generative models for labels (Bayesian support vector machine) or captions (recurrent neural network). When predicting a label/caption for a new image at test, averaging is performed across the distribution of latent codes; this is computationally efficient as a consequence of the learned CNN-based encoder. Since the framework is capable of modeling the image in the presence/absence of associated labels/captions, a new semi-supervised setting is manifested for CNN learning with images; the framework even allows unsupervised CNN learning, based on images alone.


  1. Great job for publishing such a nice article. Your article isn’t only useful but it is additionally really informative. Read more info about Label Print Toronto. Thank you because you have been willing to share information with us.

  2. An optical encoder is a device that can be used to tell the position of an object, or the distance traveled by a surface.

    An optical encoder uses the characteristics of light reflection to read a disc or cylinder which is attached to a shaft. By counting how many times the disc rotates, it can measure linear motion accurately up to 1 million counts per second.

    In order for an encoder to work properly, it needs four components: light source, photosensitive detector, logic feedback and drive electronics


Post a Comment