Slimmable Generative Adversarial Networks
Authors: Liang Hou, Zehuan Yuan, Lei Huang, Huawei Shen, Xueqi Cheng, Changhu Wang7746-7753
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our methods are validated, both quantitatively and qualitatively, by extensive experiments and a detailed ablation study. |
| Researcher Affiliation | Collaboration | 1CAS Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences 2University of Chinese Academy of Sciences 3Byte Dance AI Lab 4SKLSDE, Institute of Artificial Intelligence, Beihang University |
| Pseudocode | Yes | Algorithm 1 Training Slim GAN |
| Open Source Code | Yes | 1Code is available at https://github.com/houliangict/Slim GAN |
| Open Datasets | Yes | We employ the following datasets for main experiments: CIFAR-10/100 consists of 50k training images and 10k validation images with resolution of 32x32. CIFAR-10 has 10 classes while CIFAR-100 has 100 classes. STL-10 is resized into the size of 48x48 as done in (Miyato et al. 2018). There are 100k and 8k unlabeled images in the training set and validation set, respectively. Celeb A is a face dataset with 202,599 celebrity images with resolution of 178x218 originally. |
| Dataset Splits | Yes | CIFAR-10/100 consists of 50k training images and 10k validation images with resolution of 32x32. ... STL-10...There are 100k and 8k unlabeled images in the training set and validation set, respectively. ... Celeb A...We divide the last 19,962 images into the validation set and the remaining 182,637 images as the training set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments. |
| Software Dependencies | No | We implement all models based on Mimicry (Lee and Town 2020) using Py Torch framework. The paper does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | The optimizer is Adam with betas (β1, β2) = (0.5, 0.999) for DCGAN and (β1, β2) = (0.0, 0.9) for Res Net based SNGAN. The learning rate is α = 2 × 10−4, except Celeb A on DCGAN, which is α = 10−4. The iterations of updating the generator are T = 100k for all methods. The discriminator update steps per generator update step are K = 5 for Res Net and K = 1 for DCGAN. As for the detailed network architecture, we exactly follow that in SNGAN (Miyato et al. 2018) and cGAN-pd (Miyato and Koyama 2018). The width multiplier list is set to W = [0.25, 0.5, 0.75, 1.0]. The hyper-parameter is set as λ = 20 for both backbones on CIFAR-10 and Celeb A datasets, λ = 10 and λ = 30 for DCGAN and Res Net, respectively, on STL-10. |