Back to Search Start Over

Using Unlabeled Data for Increasing Low-Shot Classification Accuracy of Relevant and Open-Set Irrelevant Images

Authors :
Kasapis, Spiridon
Zhang, Geng
Smereka, Jonathon
Vlahopoulos, Nickolas
Publication Year :
2020

Abstract

In search, exploration, and reconnaissance tasks performed with autonomous ground vehicles, an image classification capability is needed for specifically identifying targeted objects (relevant classes) and at the same time recognize when a candidate image does not belong to anyone of the relevant classes (irrelevant images). In this paper, we present an open-set low-shot classifier that uses, during its training, a modest number (less than 40) of labeled images for each relevant class, and unlabeled irrelevant images that are randomly selected at each epoch of the training process. The new classifier is capable of identifying images from the relevant classes, determining when a candidate image is irrelevant, and it can further recognize categories of irrelevant images that were not included in the training (unseen). The proposed low-shot classifier can be attached as a top layer to any pre-trained feature extractor when constructing a Convolutional Neural Network.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2010.00721
Document Type :
Working Paper