Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Authors: Yunchen Pu, Shuyang Dai, Zhe Gan, Weiyao Wang, Guoyin Wang, Yizhe Zhang, Ricardo Henao, Lawrence Carin Duke
ICML 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 5. Experiments |
| Researcher Affiliation | Collaboration | 1Facebook, Menlo Park, CA, USA 2Duke University, Durham, NC, USA 3Microsoft Research, Redmond, WA, USA. |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code can be found at https: //github.com/sdai654416/Joint-GAN. |
| Open Datasets | Yes | edges shoes (Yu & Grauman, 2014), edges handbags (Zhu et al., 2016), Google maps aerial photos (Isola et al., 2017), labels facades (Tyleˇcek & Šára, 2013) and labels cityscapes (Cordts et al., 2016). ... Another new dataset is created based on MNIST... |
| Dataset Splits | No | The paper uses various datasets and mentions 'paired data' and 'unpaired data' settings, but it does not provide specific details on training, validation, and test dataset splits (e.g., percentages or sample counts) needed for reproduction. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions optimizers like Adam and model architectures like U-net and Patch GAN, and specific GAN variants (WGAN-GP, Pix2pix, Cycle GAN), but it does not provide specific version numbers for any software dependencies (e.g., Python, TensorFlow, PyTorch, or other libraries) that would be needed to replicate the experiment. |
| Experiment Setup | Yes | Adam (Kingma & Ba, 2014) with learning rate 0.0002 is utilized for optimization of the Joint GAN objectives. All noise vectors ϵ1, ϵ2, ϵ 1 and ϵ 2 are drawn from a N(0, I) distribution, with the dimension of each set to 100. ... For generators, we employed the U-net (Ronneberger et al., 2015)... Patch GAN is employed for the discriminator... |