SpringerBriefs in Computer Science

Composing Fisher Kernels from Deep Neural Models

A Practitioner's Approach

Authors: Azim, Tayyaba, Ahmed, Sarah

Free Preview
  • Presents a step-by-step approach to deriving a kernel from any probabilistic model belonging to the family of deep networks
  • Demonstrates the use of feature compression and selection techniques for reducing the dimensionality of Fisher vectors
  • Reviews efficient algorithms for large-scale image retrieval and classification systems, including concrete examples on different datasets
  • Provides programming solutions to help machine learning practitioners develop scalable solutions with novel ideas
see more benefits

Buy this book

eBook $54.99
price for USA in USD (gross)
  • ISBN 978-3-319-98524-4
  • Digitally watermarked, DRM-free
  • Included format: EPUB, PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Softcover $69.99
price for USA in USD
  • ISBN 978-3-319-98523-7
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
About this book

This book shows machine learning enthusiasts and practitioners how to get the best of both worlds by deriving Fisher kernels from deep learning models. In addition, the book shares insight on how to store and retrieve large-dimensional Fisher vectors using feature selection and compression techniques. Feature selection and feature compression are two of the most popular off-the-shelf methods for reducing data’s high-dimensional memory footprint and thus making it suitable for large-scale visual retrieval and classification. Kernel methods long remained the de facto standard for solving large-scale object classification tasks using low-level features, until the revival of deep models in 2006. Later, they made a comeback with improved Fisher vectors in 2010. However, their supremacy was always challenged by various versions of deep models, now considered to be the state of the art for solving various machine learning and computer vision tasks. Although the two research paradigms differ significantly, the excellent performance of Fisher kernels on the Image Net large-scale object classification dataset has caught the attention of numerous kernel practitioners, and many have drawn parallels between the two frameworks for improving the empirical performance on benchmark classification tasks. Exploring concrete examples on different data sets, the book compares the computational and statistical aspects of different dimensionality reduction approaches and identifies metrics to show which approach is superior to the other for Fisher vector encodings. It also provides references to some of the most useful resources that could provide practitioners and machine learning enthusiasts a quick start for learning and implementing a variety of deep learning models and kernel functions.

About the authors

Dr. Tayyaba Azim is an Assistant Professor at the Center for Information Technology, Institute of Management Sciences, Peshawar, Pakistan. 

Sarah Ahmed is a current research student enrolled in Masters of Computer Science program at Institute of Management Sciences Peshawar, Pakistan. 

She has received her  Bachelor’s Degree in Computer Science from Edwardes College, Peshawar,Pakistan. Her areas of interest include: Machine Learning, Computer Vision and Data-Science. Currently, her research work is centered around the feature compression and selection approaches for Fisher vectors derived from deep neural models. Her research paper: "Compression techniques for Deep Fisher Vectors" was awarded  the best paper in the area of applications at ICPRAM conference 2017. 

Reviews

 
 

Table of contents (5 chapters)

Table of contents (5 chapters)
  • Kernel Based Learning: A Pragmatic Approach in the Face of New Challenges

    Azim, Tayyaba (et al.)

    Pages 1-7

  • Fundamentals of Fisher Kernels

    Azim, Tayyaba (et al.)

    Pages 9-17

  • Training Deep Models and Deriving Fisher Kernels: A Step Wise Approach

    Azim, Tayyaba (et al.)

    Pages 19-31

  • Large Scale Image Retrieval and Its Challenges

    Azim, Tayyaba (et al.)

    Pages 33-46

  • Open Source Knowledge Base for Machine Learning Practitioners

    Azim, Tayyaba (et al.)

    Pages 47-59

Buy this book

eBook $54.99
price for USA in USD (gross)
  • ISBN 978-3-319-98524-4
  • Digitally watermarked, DRM-free
  • Included format: EPUB, PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Softcover $69.99
price for USA in USD
  • ISBN 978-3-319-98523-7
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Composing Fisher Kernels from Deep Neural Models
Book Subtitle
A Practitioner's Approach
Authors
Series Title
SpringerBriefs in Computer Science
Copyright
2018
Publisher
Springer International Publishing
Copyright Holder
The Author(s), under exclusive licence to Springer Nature Switzerland AG
eBook ISBN
978-3-319-98524-4
DOI
10.1007/978-3-319-98524-4
Softcover ISBN
978-3-319-98523-7
Series ISSN
2191-5768
Edition Number
1
Number of Pages
XIII, 59
Number of Illustrations
1 b/w illustrations, 5 illustrations in colour
Topics