Show/Hide Menu
Hide/Show Apps
anonymousUser
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Açık Bilim Politikası
Açık Bilim Politikası
Frequently Asked Questions
Frequently Asked Questions
Browse
Browse
By Issue Date
By Issue Date
Authors
Authors
Titles
Titles
Subjects
Subjects
Communities & Collections
Communities & Collections
Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery
Download
index.pdf
Date
2018-02-01
Author
Sumbul, Gencer
Cinbiş, Ramazan Gökberk
Aksoy, Selim
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
2
views
2
downloads
Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised algorithms fail to handle this problem where there is low betweenclass variance and high within-class variance for the classes of interest with small sample sizes. We study an even more extreme scenario named zero-shot learning (ZSL) in which no training example exists for some of the classes. ZSL aims to build a recognition model for new unseen categories by relating them to seen classes that were previously learned. We establish this relation by learning a compatibility function between image features extracted via a convolutional neural network and auxiliary information that describes the semantics of the classes of interest by using training samples from the seen classes. Then, we show how knowledge transfer can be performed for the unseen classes by maximizing this function during inference. We introduce a new data set that contains 40 different types of street trees in 1-ft spatial resolution aerial data, and evaluate the performance of this model with manually annotated attributes, a natural language model, and a scientific taxonomy as auxiliary information. The experiments show that the proposed model achieves 14.3% recognition accuracy for the classes with no training examples, which is significantly better than a random guess accuracy of 6.3% for 16 test classes, and three other ZSL algorithms.
Subject Keywords
Fine-grained classification
,
Object recognition
,
Zero-shot learning (ZSL)
URI
https://hdl.handle.net/11511/57907
Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
DOI
https://doi.org/10.1109/tgrs.2017.2754648
Collections
Department of Computer Engineering, Article