Triangle Generative Adversarial Networks
Authors: Zhe Gan, Liqun Chen, Weiyao Wang, Yuchen Pu, Yizhe Zhang, Hao Liu, Chunyuan Li, Lawrence Carin
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In experiments, three different kinds of domain pairs are considered, image-label, image-image and image-attribute pairs. Experiments on semi-supervised image classification, image-to-image translation and attribute-based image generation demonstrate the superiority of the proposed approach. |
| Researcher Affiliation | Academia | Zhe Gan , Liqun Chen , Weiyao Wang, Yunchen Pu, Yizhe Zhang, Hao Liu, Chunyuan Li, Lawrence Carin Duke University zhe.gan@duke.edu |
| Pseudocode | Yes | See Figure 1 for an illustration of the adversarial game and Appendix B for an algorithmic description of the training procedure. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository. |
| Open Datasets | Yes | We evaluate semi-supervised classification on the CIFAR10 dataset with 4000 labels... We first evaluate image-to-image translation on the edges2shoes dataset... To further demonstrate the importance of providing supervision of domain correspondence, we created a new dataset based on MNIST [34]... We apply our method to face images from the Celeb A dataset... we also present results on the COCO dataset [14]. |
| Dataset Splits | No | The paper mentions 'different random splits of the training data' and that 'labeled data is distributed equally across classes' but does not specify exact percentages or counts for training, validation, and testing splits, nor does it explicitly mention a dedicated validation set split. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers. It mentions following 'publically available code of Triple GAN' but does not provide specific versions of any software components. |
| Experiment Setup | No | The paper states 'we follow the publically available code of Triple GAN and use the same regularization terms and hyperparameter settings as theirs' and 'All the network architectures are provided in the Appendix.' However, it does not explicitly list the specific hyperparameter values or system-level training settings within the main text. |