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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 格式: | Conference or Workshop Item |
| 出版: |
Institute of Electrical and Electronics Engineers Inc.
2021
|
| 在線閱讀: | 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/ |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | 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. |
|---|