Composite Functional Gradient Learning of Generative Adversarial Models

Authors: Rie Johnson, Tong Zhang

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experiments on image generation show the effectiveness of our new method. We tested x ICFG on the image generation task.
Researcher Affiliation Industry 1RJ Research Consulting, Tarrytown, NY, USA 2Tencent AI Lab, Shenzhen, China.
Pseudocode Yes Algorithm 1 CFG: Composite Functional Gradient Learning of GAN; Algorithm 2 ICFG: Incremental CFG; Algorithm 3 x ICFG: Approximate ICFG; Algorithm 4 GAN (Goodfellow et al., 2014)
Open Source Code No The paper does not provide any explicit statements or links indicating that its source code is publicly available.
Open Datasets Yes We used MNIST, the Street View House Numbers dataset (SVHN) (Netzer et al., 2011), and the large-scale scene understanding (LSUN) dataset.
Dataset Splits Yes The number of real images used for training was 60K (MNIST), 521K (SVHN), 2.6 million (LSUN BR+LR), and 1.4 million (LSUN T+B). Tuning was done based on the inception score on the validation set of 10K input vectors (i.e., 10K 100-dim Gaussian vectors), and we report inception scores on the test set of 10K input vectors, disjoint from the validation set.
Hardware Specification Yes All the experiments were done using a single NVIDIA Tesla P100.
Software Dependencies No The paper mentions optimizers like rmsprop and Adam, but it does not provide specific version numbers for any software, libraries, or frameworks used (e.g., Python, PyTorch, TensorFlow, CUDA versions).
Experiment Setup Yes Table 1. Meta-parameters for x ICFG. Input: real data x 1, . . . , x n, initial generator G0(z) with generated data {G0(z1), . . . , G0(zm)}. Meta-parameter: T. ... The scaling function s(x) in ICFG was set to s(x) = 1. ... The prior pz was set to generate 100-dimensional Gaussian vectors with zero mean and standard deviation 1. All the experiments were done using a single NVIDIA Tesla P100.