How to Contribute
Sign up · Log in
1 year ago
Paper Summary: Conditional Generative Adversarial Nets
Conditional version of
Generative Adversarial Nets (GAN)
where both generator and discriminator are conditioned on some data
(class label or data from some other modality).
Link to the paper
into both the generator and discriminator as additional input layers such that
and input are combined in a joint hidden representation.
Conditioning MNIST images on class labels.
(random noise) and
mapped to hidden layers with ReLu with layer sizes of 200 and 1000 respectively and are combined to obtain ReLu layer of dimensionality 1200.
to maxout layers and the joint maxout layer is fed to sigmoid layer.
Results do not outperform the state-of-the-art results but do provide a proof-of-the-concept.
Map images (from Flickr) to labels (or user tags) to obtain the one-to-many mapping.
Extract image and text features using convolutional and language model.
Map noise and convolutional features to a single 200 dimensional representation.
Combine the representation of word vectors (corresponding to tags) and images.
While the results are not so good, they do show the potential of Conditional GANs, especially in the multimodal setting.
Read more…(199 words)
About the author:
Join the discussion. Add a reply…
Table of contents
About the author
Ready to join our community?
Sign up below to automatically get notified of new courses, get
to finish ones you subscribe to, and
lessons to read later.
Continue with Facebook
— OR —
Your Full Name
I have an account. Log in instead
By signing up, you agree to our
Natural Language Processing
UX & UI Design
How to Contribute
Upgrade to Pro
Help and FAQ
Privacy, Terms & Refunds
Get in touch
Copyright 2016-18, Compose Labs Inc. All rights reserved.