Generative-Discriminative Complementary Learning
Generative-Discriminative Complementary Learning
复制标题
DOI：
10.1609/aaai.v34i04.6126
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Yanwu Xu;Mingming Gong;Junxiang Chen;Tongliang Liu;Kun Zhang;K. Batmanghelich
中科院分区：
文献类型：
--
作者：
Yanwu Xu;Mingming Gong;Junxiang Chen;Tongliang Liu;Kun Zhang;K. Batmanghelich
大多数最先进的深度学习方法是判别方法，它对给定输入特征的标签的条件分布进行建模。这种方法的成功在很大程度上依赖于高质量的标记实例，而这些标记实例并不容易获得，特别是当候选类的数量增加时。本文主要研究互补学习问题。与普通标签不同，补充标签很容易获得，因为注释者只需要为每个实例随机选择的候选类提供是/否的答案。我们提出了一种生成-判别互补学习方法，该方法通过对条件（判别）和实例（生成）分布建模来估计普通标签。我们的方法，我们称之为互补条件GAN (CCGAN)，提高了预测普通标签的准确性，并且能够在弱监督的情况下生成高质量的实例。除了广泛的实证研究外，我们还从理论上证明了我们的模型可以从互补标记的数据中检索出真实的条件分布。
The majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and is able to generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.