Deep Network Classification by Scattering and Homotopy Dictionary Learning
This work addresses the challenge of enhancing classification performance for image recognition tasks, though it appears incremental as it builds upon existing scattering and dictionary learning methods.
The paper tackles the problem of improving classification accuracy in deep networks by introducing a sparse scattering deep convolutional neural network that uses a single dictionary matrix and a homotopy algorithm, achieving higher accuracy than AlexNet on the ImageNet 2012 dataset.
We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The network first applies a scattering transform that linearizes variabilities due to geometric transformations such as translations and small deformations. A sparse $\ell^1$ dictionary coding reduces intra-class variability while preserving class separation through projections over unions of linear spaces. It is implemented in a deep convolutional network with a homotopy algorithm having an exponential convergence. A convergence proof is given in a general framework that includes ALISTA. Classification results are analyzed on ImageNet.