Composing Fisher Kernels from Deep Neural Models
A Practitioner's Approach
Buch in deiner Nähe kaufen
Beschreibung
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
Autor*in
Tayyaba Azim
Themen in »Composing Fisher Kernels from Deep Neural Models«
Deep Models Fisher Vectors Large Scale Information Retrieval Feature Compression Techniques Feature Selection Techniques
Stimmen zu »Composing Fisher Kernels from Deep Neural Models«
()
()