Fast learning from label proportions with small bags
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00358501" target="_blank" >RIV/68407700:21230/22:00358501 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/ICIP46576.2022.9897895" target="_blank" >https://doi.org/10.1109/ICIP46576.2022.9897895</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICIP46576.2022.9897895" target="_blank" >10.1109/ICIP46576.2022.9897895</a>
Alternative languages
Result language
angličtina
Original language name
Fast learning from label proportions with small bags
Original language description
In learning from label proportions (LLP), the instances are grouped into bags, and the task is to learn an instance classifier given relative class proportions in training bags. LLP is useful when obtaining individual instance labels is impossible or costly. In this work, we focus on the case of small bags, which allows to design an algorithm that explicitly considers all consistent instance label combinations. In particular, we propose an EM algorithm alternating between optimizing a general neural network instance classifier and incorporating bag-level annotations. Using two different image datasets, we experimentally compare this method with an approach based on normal approximation and two existing LLP methods. The results show that our approach converges faster to a comparable or better solution.
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
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2022 IEEE International Conference on Image Processing (ICIP)
ISBN
978-1-6654-9620-9
ISSN
1522-4880
e-ISSN
2381-8549
Number of pages
5
Pages from-to
3156-3160
Publisher name
IEEE
Place of publication
Piscataway, NJ
Event location
Bordeaux
Event date
Oct 16, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—