Zhang Baochang, Yang Wankou, Wang Ze, Zhuo Lian, Han Jungong, Zhen Xiantong
IEEE Trans Image Process. 2019 Nov 25. doi: 10.1109/TIP.2019.2954178.
Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown. In this paper, we propose a new representation learning method, named Structure Transfer Machine (STM), which enables feature learning process to converge at the representation expectation in a probabilistic way. We theoretically show that such an expected value of the representation (mean) is achievable if the manifold structure can be transferred from the data space to the feature space. The resulting structure regularization term, named manifold loss, is incorporated into the loss function of the typical deep learning pipeline. The STM architecture is constructed to enforce the learned deep representation to satisfy the intrinsic manifold structure from the data, which results in robust features that suit various application scenarios, such as digit recognition, image classification and object tracking. Compared with state-of-the-art CNN architectures, we achieve better results on several commonly used public benchmarks.
表示学习是一个基本但具有挑战性的问题，尤其是在数据分布未知的情况下。在本文中，我们提出了一种新的表示学习方法，称为结构转移机（STM），它能够使特征学习过程以概率方式收敛于表示期望。我们从理论上表明，如果流形结构可以从数据空间转移到特征空间，那么这种表示的期望值（均值）是可以实现的。由此产生的结构正则化项，称为流形损失，被纳入到典型深度学习管道的损失函数中。STM架构的构建是为了强制使学习到的深度表示满足数据的内在流形结构，从而产生适用于各种应用场景（如数字识别、图像分类和目标跟踪）的鲁棒特征。与当前最先进的卷积神经网络（CNN）架构相比，我们在几个常用的公共基准测试中取得了更好的结果。
