论文标题
半监督的样式用于分解学习
Semi-Supervised StyleGAN for Disentanglement Learning
论文作者
论文摘要
分离学习对于获得分离的表示和可控制的产生至关重要。当前的解开方法面临着几种固有的局限性：高分辨率图像的难度，主要集中于学习分解表示形式以及由于无监督的设置而导致的非可识别性。为了减轻这些局限性，我们根据Stylegan设计了新的体系结构和损失功能（Karras等，2019），用于半监视的高分辨率分解学习。我们创建两个用于系统测试的复杂高分辨率合成数据集。我们研究有限监督的影响，发现仅使用0.25％约2.5％的标记数据就足以在合成数据集和真实数据集上进行良好的分解。我们提出了新的指标来量化发电机的可控性，并观察到分离的表示学习与可控生成之间可能存在至关重要的权衡。我们还考虑语义细颗粒图像编辑，以实现更好的概括来看不见的图像。
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on learning disentangled representations, and non-identifiability due to the unsupervised setting. To alleviate these limitations, we design new architectures and loss functions based on StyleGAN (Karras et al., 2019), for semi-supervised high-resolution disentanglement learning. We create two complex high-resolution synthetic datasets for systematic testing. We investigate the impact of limited supervision and find that using only 0.25%~2.5% of labeled data is sufficient for good disentanglement on both synthetic and real datasets. We propose new metrics to quantify generator controllability, and observe there may exist a crucial trade-off between disentangled representation learning and controllable generation. We also consider semantic fine-grained image editing to achieve better generalization to unseen images.
