U-Deepdig: Scalable Deep Decision Boundary Instance Generation

Abstract

For more than a decade, deep learning algorithms have consistently achieved and improved upon the state-of-the-art performance on image classification tasks. However, there is a general lack of understanding and knowledge about the decision boundaries carved by these modern deep neural network architectures. Recently, an algorithm called DeepDIG was introduced to generate boundary instances between two classes based on the decision regions defined by any deep neural network classifier. Although it is very effective in generating boundary instances, the underlying algorithm was designed to work with two classes at a time in a non-commutative fashion which makes it ill-suited for multi-class problems with hundreds of classes. In this work, we extend the DeepDIG algorithm so that it scales linearly with the number of classes. We show that the proposed U-DeepDIG algorithm maintains the efficacy of the original DeepDIG algorithm while being scalable and more efficient when applied to larger classification problems. We demonstrate this by applying our algorithm on MNIST, Fashion-MNIST and CIFAR10 datasets. In addition to qualitative comparisons, we also perform extensive quantitative comparison by analyzing the margin between the class boundaries and the instances generated.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 18, 2022
Accession Number
AD1191036

Entities

People

  • Charles-alban Deledalle
  • Jane Berk
  • Martin Jaszewski
  • Shibin Parameswaran

Organizations

  • Naval Information Warfare Center Pacific

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computer Vision
  • Computers
  • Computing System Architectures
  • Data Mining
  • Data Preprocessing
  • Deep Learning
  • Dimensionality Reduction
  • Image Classification
  • Image Recognition
  • Information Processing
  • Machine Learning
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks