All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

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