论文标题
跨域分解的变分相互作用信息最大化
Variational Interaction Information Maximization for Cross-domain Disentanglement
论文作者
论文摘要
跨域删除是将学习表示形式划分为域 - 不变和域特异性表示的问题，这是成功域转移或测量两个域之间语义距离的关键。基于信息理论，我们同时学习了域 - 不变和特定于域的表示，作为多个信息约束的共同目标，这不需要对抗性训练或梯度逆转层。我们得出了目标的易于限制，并提出了一个名为“交互信息自动编码器”（IIAE）的生成模型。我们的方法揭示了有关跨域拆卸的理想表示及其与变异自动编码器（VAE）的联系的见解。我们在图像到图像翻译和跨域检索任务中演示了模型的有效性。我们进一步表明，即使没有外部知识，我们的模型也可以在基于零素描的图像检索任务中实现最先进的性能。我们的实施可公开可用：https：//github.com/gr8joo/iiae
Cross-domain disentanglement is the problem of learning representations partitioned into domain-invariant and domain-specific representations, which is a key to successful domain transfer or measuring semantic distance between two domains. Grounded in information theory, we cast the simultaneous learning of domain-invariant and domain-specific representations as a joint objective of multiple information constraints, which does not require adversarial training or gradient reversal layers. We derive a tractable bound of the objective and propose a generative model named Interaction Information Auto-Encoder (IIAE). Our approach reveals insights on the desirable representation for cross-domain disentanglement and its connection to Variational Auto-Encoder (VAE). We demonstrate the validity of our model in the image-to-image translation and the cross-domain retrieval tasks. We further show that our model achieves the state-of-the-art performance in the zero-shot sketch based image retrieval task, even without external knowledge. Our implementation is publicly available at: https://github.com/gr8joo/IIAE
