Stochastic Conditional Generative Networks with Basis Decomposition
Authors: Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental success is complemented with theoretical results indicating how the perturbations introduced by the proposed sampling of basis elements can propagate to the appearance of generated images. In this section, we conduct experiments on multiple conditional generation task. |
| Researcher Affiliation | Academia | Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu Duke University {ze.w, xiuyuan.cheng, guillermo.sapiro, qiang.qiu}@duke.edu |
| Pseudocode | Yes | Algorithm 1 Optimization of the generator parameters {φ, θ} |
| Open Source Code | No | The paper does not explicitly provide a link to open-source code or state that code is released. |
| Open Datasets | Yes | Typical applications for Pix2Pix include edge maps shoes or handbags, maps satellites, and so on. centered face images in the celeb A dataset are adopted and parts of the faces are discarded by removing the center pixels. |
| Dataset Splits | No | The paper does not explicitly state specific training, validation, and test split percentages or sample counts for the datasets used. |
| Hardware Specification | Yes | The training and testing are performed on a single NVIDIA 1080Ti graphic card with 11GB memory. |
| Software Dependencies | No | The paper mentions using 'PyTorch' for implementation but does not specify a version number or other software dependencies with their versions. |
| Experiment Setup | No | The paper describes network architectures and loss functions, but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed optimizer settings for the experimental setup. |