Structured Sparse Convolutional Autoencoder

Abstract

This paper aims to improve the feature learning in Convolutional Networks (Convnet) by capturing the structure of objects. A new sparsity function is imposed on the extracted featuremap to capture the structure and shape of the learned object, extracting interpretable features to improve the prediction performance. The proposed algorithm is based on organizing the activation within and across featuremap by constraining the node activities through ${\ell }_2$ and ${\ell }_1$ normalization in a structured form.

The paper need some improvements

References in corpus (2)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Theano: new features and speed improvements