论文标题
调查辅助分类器gans在低数据状态下图像分类的潜力
Investigating the Potential of Auxiliary-Classifier GANs for Image Classification in Low Data Regimes
论文作者
论文摘要
生成对抗网络（GAN）在增强数据集并提高卷积神经网络（CNN）的性能方面表现出了希望。但是他们引入了更多的超参数调整，以及需要额外的时间和计算能力来培训CNN补充的能力。在这项工作中，我们研究了辅助分类器gan（AC-GAN）作为图像分类的“一站式”架构的潜力，尤其是在低数据制度中。此外，我们探索了对典型的AC-GAN框架的修改，改变了发电机的潜在空间采样方案，并采用了沃斯坦的损失，并进行了梯度惩罚，以稳定对图像合成和分类的同时训练。通过对不同分辨率和复杂性的图像进行实验，我们证明了AC-GAN在图像分类中表现出希望，从而通过标准CNN实现了竞争性能。在没有大量培训数据的情况下，这些方法可以用作具有特殊效用的“多合一”框架。
Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural networks' (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the need for additional time and computational power to train supplementary to the CNN. In this work, we examine the potential for Auxiliary-Classifier GANs (AC-GANs) as a 'one-stop-shop' architecture for image classification, particularly in low data regimes. Additionally, we explore modifications to the typical AC-GAN framework, changing the generator's latent space sampling scheme and employing a Wasserstein loss with gradient penalty to stabilize the simultaneous training of image synthesis and classification. Through experiments on images of varying resolutions and complexity, we demonstrate that AC-GANs show promise in image classification, achieving competitive performance with standard CNNs. These methods can be employed as an 'all-in-one' framework with particular utility in the absence of large amounts of training data.
