Zero-shot learning with Fast RCNN and Mask RCNN through semantic attribute Mapping
Journal Title: International Journal of Engineering and Science Invention - Year 2018, Vol 7, Issue 5
Abstract
Machine learning applications increasingly address large and diverse data sets. While this leads to an abundance of some classes of data, it also uncovers objects that defy categorization in previously seen classes. Learning from sparse data set of images is challenging. The task of classifying samples taken from categories where no training examples exist is known as zero-shot learning. This problem has interest both from the practical standpoint of automatically labelling novel items, thereby saving the time needed to retrain classifiers and from the scientific standpoint of understanding how humans perform the task. Zero shot learning is a hierarchical approach to image classification problems that have no training examples. Zero shot learning is a combination of hierarchical and attribute based classification methods; the former gives a projected position in an established hierarchy, while the latter provides a ranked listing of potential classes and their estimated probabilities. Here we are using two hierarchical methods, Fast RCNN and Mask RCNN. Finally we compare the performance of both and will find the most efficient one.
Authors and Affiliations
Jilsha P J, Chinchu Krishna
Keywords
Related Articles
- EP ID EP397093
- DOI -
- Views 106
- Downloads 0
Generalized Weibull Pareto Distribution To Analyze The Association Of Estrogen And Progesterone Hormone With Mammographic Density Phenotypes.
A Generalized Weibull-Pareto Distribution is used to analyze the association of estrogen and progesterone hormone with mammographic density phenotypes in premenopausal women. We know that these are the key factor in deve...
The Effect of Color on Urban Beautification and Peace of Citizens
Color has the most important role in the behavior pattern of urban human and is a social powerful element that in addition to the mission and task of conveying messages has the task of visual appeal of the city. Despite...
Design And Analysis of A Hydraulic Biogas Digester Using Agricultural Biomass
Agricultural Biomass represents one of the most important sources of clean energy which can be used for domestic energy source, using different technologies. This can replace, partially or totally, the existing fossil fu...
Exploration Tool for Instruction Memory Organisations Based On Accurate Cycle-Level Energy Modelling
The plan of current implanted frameworks is obliged by the necessities of present day installed applications. A considerable lot of these applications require not just supported operation for drawn out stretches of time,...
An Elite Particle Swarm Optimization Algorithm Based On Quadratic Approximations For High-Dimension Bilevel Single Objective Programming Problems
Bilevel programming problem (BLP) is a nested optimization problem that contains one optimization task as a constraint to another optimization task. However, current existing algorithms for BLP often need enormous comput...