LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
2021
Generative adversarial network
A generative model comprising a generator trained against a discriminator that distinguishes generated samples from observed data.
A generative model comprising a generator trained against a discriminator that distinguishes generated samples from observed data.
The generator’s latent space can encode directions associated with transformations of generated samples.