Conditional Image Synthesis with Auxiliary Classifier GANs
Authors: Augustus Odena, Christopher Olah, Jonathon Shlens
ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128 128 resolution image samples exhibiting global coherence. We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models. These analyses demonstrate that high resolution samples provide class information not present in low resolution samples. Across 1000 Image Net classes, 128 128 samples are more than twice as discriminable as artificially resized 32 32 samples. In addition, 84.7% of the classes have samples exhibiting diversity comparable to real Image Net data. |
| Researcher Affiliation | Industry | Augustus Odena 1 Christopher Olah 1 Jonathon Shlens 1, 1Google Brain. Correspondence to: Augustus Odena <augustusodena@google.com>. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the methodology described in this paper. It only links to generated samples and a third-party Inception-v3 implementation. |
| Open Datasets | Yes | We train several AC-GAN models on the Image Net data set (Russakovsky et al., 2015). and Instead we compare with previous state-of-the-art results on CIFAR-10 using a lower spatial resolution (32 32). |
| Dataset Splits | No | The paper uses standard datasets like ImageNet and CIFAR-10 which have predefined splits, but it does not explicitly specify the training, validation, or test dataset splits used for their experiments, only how samples for evaluation metrics like Inception score were grouped. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper mentions the use of an 'Inception network' and a 'Leaky ReLU nonlinearity', but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | Yes | We train two variants of the model architecture for generating images at 128 128 and 64 64 spatial resolutions. and We train 100 AC-GAN models each on images from just 10 classes for 50000 mini-batches of size 100. |