The Structure Transfer Machine Theory and Applications
This work addresses robust feature learning for applications such as digit recognition and image classification, but it appears incremental as it builds on existing deep learning pipelines with a new regularization term.
The authors tackled representation learning under unknown data distributions by proposing the Structure Transfer Machine (STM), which incorporates a manifold loss to enforce structure preservation, achieving better results than state-of-the-art CNNs on benchmarks like digit recognition and image classification.
Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown. We propose a new representation learning method, termed 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 to state-of-the-art CNN architectures, we achieve the better results on several commonly used benchmarks\footnote{The source code is available. https://github.com/stmstmstm/stm }.