Composing Fisher Kernels from Deep Neural Models

A Practitioner's Approach

Nonfiction, Computers, Advanced Computing, Engineering, Computer Vision, Science & Nature, Technology, Electronics, General Computing
Cover of the book Composing Fisher Kernels from Deep Neural Models by Tayyaba Azim, Sarah Ahmed, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Tayyaba Azim, Sarah Ahmed ISBN: 9783319985244
Publisher: Springer International Publishing Publication: August 23, 2018
Imprint: Springer Language: English
Author: Tayyaba Azim, Sarah Ahmed
ISBN: 9783319985244
Publisher: Springer International Publishing
Publication: August 23, 2018
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer International Publishing

Cover of the book English as a Global Language in China by Tayyaba Azim, Sarah Ahmed
Cover of the book AI Approaches to the Complexity of Legal Systems by Tayyaba Azim, Sarah Ahmed
Cover of the book Making Better Decisions Using Systems Thinking by Tayyaba Azim, Sarah Ahmed
Cover of the book Linear and Nonlinear Programming by Tayyaba Azim, Sarah Ahmed
Cover of the book Quantum Dynamics and Laser Control for Photochemistry by Tayyaba Azim, Sarah Ahmed
Cover of the book Foundations of Heterogeneous Integration: An Industry-Based, 2.5D/3D Pathfinding and Co-Design Approach by Tayyaba Azim, Sarah Ahmed
Cover of the book Culture, Diversity and Heritage: Major Studies by Tayyaba Azim, Sarah Ahmed
Cover of the book How to Overcome the Antibiotic Crisis by Tayyaba Azim, Sarah Ahmed
Cover of the book Ontology-based Procedural Modelling of Traversable Buildings Composed by Arbitrary Shapes by Tayyaba Azim, Sarah Ahmed
Cover of the book Natural and Artificial Reasoning by Tayyaba Azim, Sarah Ahmed
Cover of the book Edgar Rubin and Psychology in Denmark by Tayyaba Azim, Sarah Ahmed
Cover of the book Information Systems Architecture and Technology: Proceedings of 39th International Conference on Information Systems Architecture and Technology – ISAT 2018 by Tayyaba Azim, Sarah Ahmed
Cover of the book New Metropolitan Perspectives by Tayyaba Azim, Sarah Ahmed
Cover of the book DNA Information: Laws of Perception by Tayyaba Azim, Sarah Ahmed
Cover of the book Internet Science by Tayyaba Azim, Sarah Ahmed
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy