Cover Image

Analysis of Unsupervised Loss Functions for Homography Estimation

Neural networks proved their ability in complex classification and regression problems using labeled data. Recent trends have shown the impressive performance of neural networks in more complex problems like estimating ego-motion and homography tasks. Due to complexity and time consumption for label...

Full description

Saved in:
Bibliographic Details
Main Authors: Gadipudi, N., Elamvazuthi, I., Lu, C.-K., Paramasivam, S., Jegadeeshwaran, R.
Format: Conference or Workshop Item
Published: Institute of Electrical and Electronics Engineers Inc. 2021
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124144798&doi=10.1109%2fICIAS49414.2021.9642689&partnerID=40&md5=941af55a7463560f685a188c8dbe5e96
http://eprints.utp.edu.my/29207/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.29207
record_format eprints
spelling my.utp.eprints.292072022-03-25T01:11:51Z Analysis of Unsupervised Loss Functions for Homography Estimation Gadipudi, N. Elamvazuthi, I. Lu, C.-K. Paramasivam, S. Jegadeeshwaran, R. Neural networks proved their ability in complex classification and regression problems using labeled data. Recent trends have shown the impressive performance of neural networks in more complex problems like estimating ego-motion and homography tasks. Due to complexity and time consumption for labeling data, researchers tend to exhibit their attentiveness towards unsupervised data-based learning. However, there are no standard loss functions used for image reconstruction and less attention is drawn towards the loss functions than the end to end network architectures. In this paper, we carefully analyze and evaluate the two most commonly used loss functions for the homography estimation task. © 2021 IEEE. Institute of Electrical and Electronics Engineers Inc. 2021 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124144798&doi=10.1109%2fICIAS49414.2021.9642689&partnerID=40&md5=941af55a7463560f685a188c8dbe5e96 Gadipudi, N. and Elamvazuthi, I. and Lu, C.-K. and Paramasivam, S. and Jegadeeshwaran, R. (2021) Analysis of Unsupervised Loss Functions for Homography Estimation. In: UNSPECIFIED. http://eprints.utp.edu.my/29207/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Neural networks proved their ability in complex classification and regression problems using labeled data. Recent trends have shown the impressive performance of neural networks in more complex problems like estimating ego-motion and homography tasks. Due to complexity and time consumption for labeling data, researchers tend to exhibit their attentiveness towards unsupervised data-based learning. However, there are no standard loss functions used for image reconstruction and less attention is drawn towards the loss functions than the end to end network architectures. In this paper, we carefully analyze and evaluate the two most commonly used loss functions for the homography estimation task. © 2021 IEEE.
format Conference or Workshop Item
author Gadipudi, N.
Elamvazuthi, I.
Lu, C.-K.
Paramasivam, S.
Jegadeeshwaran, R.
spellingShingle Gadipudi, N.
Elamvazuthi, I.
Lu, C.-K.
Paramasivam, S.
Jegadeeshwaran, R.
Analysis of Unsupervised Loss Functions for Homography Estimation
author_facet Gadipudi, N.
Elamvazuthi, I.
Lu, C.-K.
Paramasivam, S.
Jegadeeshwaran, R.
author_sort Gadipudi, N.
title Analysis of Unsupervised Loss Functions for Homography Estimation
title_short Analysis of Unsupervised Loss Functions for Homography Estimation
title_full Analysis of Unsupervised Loss Functions for Homography Estimation
title_fullStr Analysis of Unsupervised Loss Functions for Homography Estimation
title_full_unstemmed Analysis of Unsupervised Loss Functions for Homography Estimation
title_sort analysis of unsupervised loss functions for homography estimation
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2021
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124144798&doi=10.1109%2fICIAS49414.2021.9642689&partnerID=40&md5=941af55a7463560f685a188c8dbe5e96
http://eprints.utp.edu.my/29207/
_version_ 1738656933172215808
score 13.211869

Similar Items