Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets

2016/03/22 by Vishwajeet Singh, Singh, Vishwajeet, Killamsetti Ravi Kumar +4
Computer Science · Mathematics · #FOS: Computer and information sciences #Face and Expression Recognition #I.5 #I.5.3 #Image Retrieval and Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1607.01354

12 pages, 8 figures and 8 tables

arxiv created 2016/03/22 · openalex publication_date 2016/03/22 · arxiv updated 2016/07/06 · openalex created_date 2016/07/22 · openalex updated_date 2026/07/28

Abstract

As machine learning is applied to an increasing variety of complex problems, which are defined by high dimensional and complex data sets, the necessity for task oriented feature learning grows in importance. With the advancement of Deep Learning algorithms, various successful feature learning techniques have evolved. In this paper, we present a novel way of learning discriminative features by training Deep Neural Nets which have Encoder or Decoder type architecture similar to an Autoencoder. We demonstrate that our approach can learn discriminative features which can perform better at pattern classification tasks when the number of training samples is relatively small in size.

Citations

• Gradient-based learning applied to document recognition
• Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models

Related

• Learning Discriminative Features with Class Encoder
• Learning a Discriminant Latent Space with Neural Discriminant Analysis
• Learning Discriminative Features via Label Consistent Neural Network
• Discriminative Autoencoder for Feature Extraction: Application to Character Recognition
• Learning Fine-grained Features via a CNN Tree for Large-scale Classification