Fine-grained object recognition and zero-shot learning in multispectral imagery
Date
2018Source Title
2018 26th Signal Processing and Communications Applications Conference (SIU)
Publisher
IEEE
Language
Turkish
Type
Conference PaperItem Usage Stats
217
views
views
268
downloads
downloads
Abstract
We present a method for fine-grained object recognition problem, that aims to recognize the type of an object among a large number of sub-categories, and zero-shot learning scenario on multispectral images. In order to establish a relation between seen classes and new unseen classes, a compatibility function between image features extracted from a convolutional neural network and auxiliary information of classes is learnt. Knowledge transfer for unseen classes is carried out by maximizing this function. Performance of the model (15.2%) evaluated with manually annotated attributes, a natural language model, and a scientific taxonomy as auxiliary information is promisingly better than the other methods for 16 test classes.