Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
复制标题
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Utkarsh Ojha;Krishna Kumar Singh;Cho-Jui Hsieh;Yong Jae Lee
中科院分区：
文献类型：
--
作者：
Utkarsh Ojha;Krishna Kumar Singh;Cho-Jui Hsieh;Yong Jae Lee
我们提出了一种新的无监督生成模型，学习从类不平衡数据的其他低层次方面解开对象身份。我们首先调查了InfoGAN [10]关于均匀性假设的问题，并证明了它在不平衡数据中正确解开对象身份的无效性。我们的关键思想是发现离散的潜在因素的变化不变的身份保持变换在真实的图像，并使用它作为一个信号来学习适当的潜在分布代表对象的身份。在阿尔蒂官方（MNIST，3D汽车，3D椅子，ShapeNet）和现实世界（YouTube-Faces）不平衡数据集上的实验证明了我们的方法在解开对象身份作为变化的潜在因素方面的有效性
We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. We first investigate the issues surrounding the assumptions about uniformity made by InfoGAN [10], and demonstrate its ineffectiveness to properly disentangle object identity in imbalanced data. Our key idea is to make the discovery of the discrete latent factor of variation invariant to identity-preserving transformations in real images, and use that as a signal to learn the appropriate latent distribution representing object identity. Experiments on both artificial (MNIST, 3D cars, 3D chairs, ShapeNet) and real-world (YouTube-Faces) imbalanced datasets demonstrate the effectiveness of our method in disentangling object identity as a latent factor of variation