Deep Network Classification by Scattering and Homotopy Dictionary LearningDownload PDF

25 Sept 2019, 19:17 (edited 10 Feb 2022)ICLR 2020 Conference Blind SubmissionReaders: Everyone
  • Original Pdf: pdf
  • Code: [![github](/images/github_icon.svg) j-zarka/SparseScatNet](https://github.com/j-zarka/SparseScatNet)
  • TL;DR: A scattering transform followed by supervised dictionary learning reaches a higher accuracy than AlexNet on ImageNet.
  • Abstract: 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.
  • Keywords: dictionary learning, scattering transform, sparse coding, imagenet
8 Replies

Loading