Effective Data Augmentation with Multi-Domain Learning GANs
Authors: Shin'ya Yamaguchi, Sekitoshi Kanai, Takeharu Eda6566-6574
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We experimentally evaluate the advantages of Domain Fusion in image classification tasks on 3 target datasets: CIFAR-100, FGVC-Aircraft, and Indoor Scene Recognition. |
| Researcher Affiliation | Collaboration | Shin ya Yamaguchi,1 Sekitoshi Kanai,1,2 Takeharu Eda1 1NTT Software Innovation Center 2Keio University Tokyo, Japan {shinya.yamaguchi.mw, sekitoshi.kanai.fu, takeharu.eda.bx}@hco.ntt.co.jp |
| Pseudocode | Yes | Algorithm 1 Multi-Domain Training of Domain Fusion |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-sourcing of its code for the Domain Fusion methodology. |
| Open Datasets | Yes | The target task was the image classification on CIFAR-100 (Krizhevsky and Hinton 2009), FGVCAircraft (Maji et al. 2013), and Indoor Scene Recognition (ISR) (Quattoni and Torralba 2009). Table 1 describes the list of the candidate for the outer dataset. These are image datasets of various domain that are often used for the evaluation of computer vision tasks. |
| Dataset Splits | Yes | We used 50,000 samples (4,000 real images + 46,000 generated images) as training set, and 1,000 real images as validation set. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions using "Res Net-based SNGAN" as an implementation of conditional GANs and Adam optimizer, but it does not specify software dependencies with version numbers (e.g., Python, TensorFlow, PyTorch, CUDA versions). |
| Experiment Setup | Yes | We trained a GAN for 50k iterations with a batch of 256 using Adam (β1 = 0, β2 = 0.9)...The learning rate of generators and discriminators were 1.0 10 4 and 4.0 10 4, respectively. We linearly shifted both the learning rates to 0...In multi-domain training, we set α = 0.5 for all experiments...The architecture for the target classifier was Res Net-18 for 224 224 (He et al. 2016) with Adam optimizer for 100 epochs, batches of size 512. We selected the batch size by grid search over 128, 256, 512, 1024...The hyperparameters for Adam were αAdam = 2.0 10 4, β1 = 0, β2 = 0.9. |