A new semi-supervised method improving optical flow on distant domains
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00338252" target="_blank" >RIV/68407700:21230/20:00338252 - isvavai.cz</a>
Result on the web
<a href="https://data.vicos.si/cvww20/22.pdf" target="_blank" >https://data.vicos.si/cvww20/22.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
A new semi-supervised method improving optical flow on distant domains
Original language description
We propose a semi-supervised approach to learning by formulating the optimization as constrained gradient descent on a loss function that includes unsupervised terms. The method is demonstrated on semi-supervised optical flow training that promotes photo-consistency and smoothness of the flow. We show that the unsupervised objective significantly improves the estimation on a distant domain while maintaining the performance on the original domain. As a result, we achieve state-of-the-art results on the Creative Flow+ dataset among CNN based methods that did not train on any samples from the dataset.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 25th Computer Vision Winter Workshop Conference February 3-5, 2020, Rogaška Slatina, Slovenia
ISBN
978-961-90901-9-0
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
37-45
Publisher name
Slovenian Pattern Recognition Society
Place of publication
Ljubljana
Event location
Rogaška Slatina
Event date
Feb 3, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—