Learning Hierarchical Features from Deep Generative Models
Authors: Shengjia Zhao, Jiaming Song, Stefano Ermon
ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We train a factorized three layer VAE in Equation (4) on MNIST by optimizing the ELBO criteria from Equation (5). We experimentally validate these intuitions in Figure 3, where we train a three layer Markov HVAE with factorized Gaussian conditionals p(zℓ|zℓ+1) on MNIST and SVHN. Details about the experimental setup are explained in the Appendix. We train VLAE over several datasets and visualize the semantic meaning of the latent code. In Figure 5, we visualize generation results from MNIST, where the model is a 3-layer VLAE with 2 dimensional latent code (z) at each layer. Next we evaluate VLAE on the Street View House Number (SVHN, Netzer et al. (2011)) dataset, where it is significantly more challenging to learn interpretable representations since it is relatively noisy, containing certain digits which do not appear in the center. Finally, we display compelling results from another challenging dataset, Celeb A (Liu et al., 2015), which includes 200,000 celebrity images. |
| Researcher Affiliation | Academia | 1Stanford University. |
| Pseudocode | No | The paper does not include any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code is available at https://github.com/ermongroup/Variational Ladder-Autoencoder |
| Open Datasets | Yes | We train a factorized three layer VAE in Equation (4) on MNIST... We experimentally validate these intuitions in Figure 3, where we train a three layer Markov HVAE... on MNIST and SVHN. We train VLAE over several datasets... Next we evaluate VLAE on the Street View House Number (SVHN, Netzer et al. (2011)) dataset... Finally, we display compelling results from another challenging dataset, Celeb A (Liu et al., 2015)... |
| Dataset Splits | No | The paper mentions training on datasets but does not explicitly provide details about training, validation, or test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., GPU/CPU models, memory, or cloud computing instances) used for running the experiments. |
| Software Dependencies | No | The paper mentions the existence of code (available at a GitHub link) but does not list specific software dependencies with version numbers (e.g., PyTorch 1.x, Python 3.x). |
| Experiment Setup | No | The paper states 'Details about the experimental setup are explained in the Appendix' (which is not provided in the main text). Therefore, no specific hyperparameter values or training configurations are detailed within the main body of the paper. |