Unsupervised Feature Learning by Deep Sparse Coding
This addresses the problem of learning hierarchical features without labeled data for computer vision researchers, though it appears incremental as it builds on existing sparse coding methods.
The paper tackled unsupervised feature learning for visual object recognition by proposing Deep Sparse Coding (DeepSC), a multi-layer extension of sparse coding with a sparse-to-dense module, achieving state-of-the-art performance on multiple tasks.
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework is that it connects the sparse-encoders from different layers by a sparse-to-dense module. The sparse-to-dense module is a composition of a local spatial pooling step and a low-dimensional embedding process, which takes advantage of the spatial smoothness information in the image. As a result, the new method is able to learn several levels of sparse representation of the image which capture features at a variety of abstraction levels and simultaneously preserve the spatial smoothness between the neighboring image patches. Combining the feature representations from multiple layers, DeepSC achieves the state-of-the-art performance on multiple object recognition tasks.