Authors:
Sarah Ahmed
and
Tayyaba Azim
Affiliation:
Institute of Management Sciences, Pakistan
Keyword(s):
Fisher Vectors (FV), Restricted Boltzmann Machine (RBM), k-Nearest Neighbor (k-nn), Principal Component Analysis (PCA), Parametric t-SNE, Spectral Hashing.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Cardiovascular Imaging and Cardiography
;
Cardiovascular Technologies
;
Classification
;
Computational Intelligence
;
Computational Learning Theory
;
Computer Vision, Visualization and Computer Graphics
;
Data Engineering
;
Embedding and Manifold Learning
;
Feature Selection and Extraction
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
ICA, PCA, CCA and other Linear Models
;
Image Understanding
;
Information Retrieval
;
Kernel Methods
;
Methodologies and Methods
;
Model Selection
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Object Recognition
;
Ontologies and the Semantic Web
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Software Engineering
;
Sparsity
;
Theory and Methods
Abstract:
This paper investigates the use of efficient compression techniques for Fisher vectors derived from deep architectures such as Restricted Boltzmann machine (RBM). Fisher representations have recently created a surge of interest by proving their worth for large scale object recognition and retrieval problems, however they suffer from the problem of large dimensionality as well as have some intrinsic properties that make them unique from the conventional bag of visual words (BoW) features. We have shown empirically which of the normalisation and state of the art compression techniques is well suited for deep Fisher vectors making them amenable for large scale visual retrieval with reduced memory footprint. We further show that the compressed Fisher vectors give impressive classification results even with costless linear classifiers like k-nearest neighbour.