Zero-Shot Object Recognition System Based on Topic Model

Object recognition systems usually require fully complete manually labeled training data to train classifier. In this paper, we study the problem of object recognition, where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on human-machine systems 2015-08, Vol.45 (4), p.518-525
Main Authors: Wai Lam Hoo, Chee Seng Chan
Format: Article
Language:English
Subjects:
Accuracy
Histograms
Image understanding
Object recognition
Radio frequency
Semantics
topic model
Training
Vegetation
zero-shot learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Object recognition systems usually require fully complete manually labeled training data to train classifier. In this paper, we study the problem of object recognition, where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a novel zero-shot learning strategy that utilizes the topic model and hierarchical class concept. Our proposed method advanced where cumbersome human annotation stage (i.e., attribute-based classification) is eliminated. We achieve comparable performance with state-of-the-art algorithms in four public datasets: PubFig (67.09%), Cifar-100 (54.85%), Caltech-256 (52.14%), and Animals with Attributes (49.65%), when unseen classes exist in the classification task.
ISSN:2168-2291
2168-2305
DOI:10.1109/THMS.2014.2358649