Perceptual Pyramid Adversarial Networks for Text-to-Image Synthesis
Authors: Lianli Gao, Daiyuan Chen, Jingkuan Song, Xing Xu, Dongxiang Zhang, Heng Tao Shen8312-8319
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that our PPAN sets new records for text-to-image synthesis on two benchmark datasets: CUB (i.e., 4.38 Inception Score and .290 Visual-semantic Similarity) and Oxford-102 (i.e., 3.52 Inception Score and .297 Visual-semantic Similarity). |
| Researcher Affiliation | Academia | Lianli Gao,1 Daiyuan Chen,1 Jingkuan Song,1 Xing Xu,1 Dongxiang Zhang,1 Heng Tao Shen1 1Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China. |
| Pseudocode | No | The paper describes its method using diagrams and prose, but it does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | The CUB dataset (Wah et al. 2011) contains 8855 and 2933 images for training and testing, totally belonging to 200 categories. The Oxford-102 dataset (Nilsback and Zisserman 2008) consists of 7034 and 1155 images for training and testing, a total of 102 categories. |
| Dataset Splits | No | The paper mentions training and testing sets (e.g., 'The CUB dataset... contains 8855 and 2933 images for training and testing'), but it does not explicitly mention a separate validation split or its size. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running its experiments, such as GPU/CPU models or memory. |
| Software Dependencies | No | The paper mentions software components like 'Adam' optimizer, 'VGG16 network', and 'Inception models', but it does not provide specific version numbers for these or for any underlying frameworks (e.g., Python, PyTorch, TensorFlow). |
| Experiment Setup | Yes | By default, we set λ1 = β1 = λ2 = β2 = 1, λ3 = 1e 07, and β3 = 100 for all datasets, λ4 = 4 for CUB and Oxford-102 dataset. |