Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

DeepDyve requires Javascript to function. Please enable Javascript on your browser to continue.

Composing Fisher Kernels from Deep Neural Models

Part of the SpringerBriefs in Computer Science Book Series

DOI: 10.1007/978-3-319-98524-4

ISBN: 978-3-319-98523-7

Publisher: Springer International Publishing - Springer Journals

Aug 24, 2018

LitStream

Chapter 1Kernel Based Learning: A Pragmatic Approach in the Face of New Challenges

Azim, Tayyaba; Ahmed, Sarah

Pages: 1 –7

[This chapter is not aimed at replacing literature on introduction to kernel methods or Fisher kernels. There are some excellent text books and tutorials on the topic by Schölkopf and Smola (Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press...
LitStream

Chapter 2Fundamentals of Fisher Kernels

Azim, Tayyaba; Ahmed, Sarah

Pages: 9 –17

[This chapter introduces a specific genre of kernels that draws a formal connection between the generative and discriminative models of learning. Both the paradigms offer unique complementary advantages over one another, yet there always existed a need to combine the best of both the worlds for...
LitStream

Chapter 3Training Deep Models and Deriving Fisher Kernels: A Step Wise Approach

Azim, Tayyaba; Ahmed, Sarah

Pages: 19 –31

[Deep networks and Fisher kernels are two competitive approaches showing strides of progress and improvement for computer vision tasks in specific the large scale object categorisation problem. One of the recent developments in this regard has been the use of a hybrid approach that encodes higher...
LitStream

Chapter 4Large Scale Image Retrieval and Its Challenges

Azim, Tayyaba; Ahmed, Sarah

Pages: 33 –46

[Fisher vector encoding from deep architectures has shown significant improvement in the performance of classification and retrieval tasks. Despite significant benefit of Fisher vectors for classification and retrieval problems, they suffer from the problem of high dimensionality giving rise to...
LitStream

Chapter 5Open Source Knowledge Base for Machine Learning Practitioners

Azim, Tayyaba; Ahmed, Sarah

Pages: 47 –59

[In this chapter, we provide references to some of the most useful resources that could provide practitioners a quick start for learning and implementing a variety of deep learning models, kernel functions, Fisher vector encodings and feature condensation techniques. Not only can the users...

results per page

Prev
1
Next

Browse All eBooks