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 86
- Downloads 0
Renewable Energy Resource of Power Generation Using Solar Photovoltaic And Wind Energy
With increasing demand for energy and with fast depleting conventional sources of energy such as coal, petroleum, natural gas, etc. the non-conventional sources of energy such as energy from sun, wind, biomass, tidal ene...
A New Approach For Optimal Solution Of Transportation Problem
The classical Transportation problem is one of the many well -structured problems in operational research that has been extensively studied in the literature. The transportation problem is one of the subclasses of the li...
Computational Analysis Of Aerodynamic Characteristics With Different Overlap Ratio Using CFD
Numerical investigation was carried out to find out aerodynamic characteristics with help of commercial computational fluid dynamic (CFD) software GAMBIT and FLUENT. In this analysis three different models with different...
A Study on Importance and Effectiveness of Cognitive ELearning in Distance Education of Rural Areas
The main focus of distance education is the instructional system design and technology. It aims to deliver education to the students who are not physically present in a traditional classroom. The courses offered in dista...
Design of Roba Mutiplier Using Booth Signed Multiplier and Brent Kung Adder
Approximate Circuits Are Becoming An Effective Solution To Co Accurately Operating Circuits If Energy Efficiency Is Concerned And The Application Is Error Tolerant. In This Paper An Approximate Multiplier Which Is Based...