我们可以再看原论文摘要:
注:如果各位看官不习惯英语,可直接跳过看下面的翻译:)
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.
近年来,通过卷积网络(CNN)进行监督学习的方法已在计算机视觉应用中得到了广泛采用。相比之下,CNN的无监督学习受到的关注较少。在这项工作中,我们希望帮助缩小CNN在监督学习与无监督学习之间的差距。我们介绍一种遵循着一些网络结构设计约束的深度卷积生成对抗网络(DCGAN),并证明它是无监督学习的强大候选者。在各种图像数据集上的训练结果令人信服,即深度卷积生成器和判别器都学习到了从对象局部到场景的特征层次结构。此外,我们将学习到的特征用于新颖的任务——这更进一步展示了其作为通用图像特征表示的适用性。
作为几乎是初学者入门GAN的第一个上手实操的GAN变体,我经常会遇到他们这么一个问题:“GAN也太辣鸡了吧,生成的图像都啥玩意儿呢”