LatentGAN Autoencoder: Learning Disentangled Latent Distribution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916572885417984 |
|---|---|
| author | Kalwar, Sanket Aich, Animikh Dixit, Tanay Chhabra, Adit |
| author_facet | Kalwar, Sanket Aich, Animikh Dixit, Tanay Chhabra, Adit |
| contents | In autoencoder, the encoder generally approximates the latent distribution over the dataset, and the decoder generates samples using this learned latent distribution. There is very little control over the latent vector as using the random latent vector for generation will lead to trivial outputs. This work tries to address this issue by using the LatentGAN generator to directly learn to approximate the latent distribution of the autoencoder and show meaningful results on MNIST, 3D Chair, and CelebA datasets, an additional information-theoretic constrain is used which successfully learns to control autoencoder latent distribution. With this, our model also achieves an error rate of 2.38 on MNIST unsupervised image classification, which is better as compared to InfoGAN and AAE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_02010 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | LatentGAN Autoencoder: Learning Disentangled Latent Distribution Kalwar, Sanket Aich, Animikh Dixit, Tanay Chhabra, Adit Computer Vision and Pattern Recognition Machine Learning In autoencoder, the encoder generally approximates the latent distribution over the dataset, and the decoder generates samples using this learned latent distribution. There is very little control over the latent vector as using the random latent vector for generation will lead to trivial outputs. This work tries to address this issue by using the LatentGAN generator to directly learn to approximate the latent distribution of the autoencoder and show meaningful results on MNIST, 3D Chair, and CelebA datasets, an additional information-theoretic constrain is used which successfully learns to control autoencoder latent distribution. With this, our model also achieves an error rate of 2.38 on MNIST unsupervised image classification, which is better as compared to InfoGAN and AAE. |
| title | LatentGAN Autoencoder: Learning Disentangled Latent Distribution |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2204.02010 |