Self-supervised Learning from Semantically Imprecise Data

Clemens-Alexander Brust, Björn Barz, Joachim Denzler, Joachim Denzler

2022

Abstract

Learning from imprecise labels such as “animal” or “bird”, but making precise predictions like “snow bunting” at inference time is an important capability for any classifier when expertly labeled training data is scarce. Contributions by volunteers or results of web crawling lack precision in this manner, but are still valuable. And crucially, these weakly labeled examples are available in larger quantities for lower cost than high-quality bespoke training data. CHILLAX, a recently proposed method to tackle this task, leverages a hierarchical classifier to learn from imprecise labels. However, it has two major limitations. First, it does not learn from examples labeled as the root of the hierarchy, e.g., “object”. Second, an extrapolation of annotations to precise labels is only performed at test time, where confident extrapolations could be already used as training data. In this work, we extend CHILLAX with a self-supervised scheme using constrained semantic extrapolation to generate pseudo-labels. This addresses the second concern, which in turn solves the first problem, enabling an even weaker supervision requirement than CHILLAX. We evaluate our approach empirically, showing that our method allows for a consistent accuracy improvement of 0.84 to 1.19 percent points over CHILLAX and is suitable as a drop-in replacement without any negative consequences such as longer training times.

Paper Citation

in Harvard Style

Brust C., Barz B. and Denzler J. (2022). Self-supervised Learning from Semantically Imprecise Data. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 27-35. DOI: 10.5220/0010766700003124

in Bibtex Style

@conference{visapp22,
author={Clemens-Alexander Brust and Björn Barz and Joachim Denzler},
title={Self-supervised Learning from Semantically Imprecise Data},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={27-35},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010766700003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Self-supervised Learning from Semantically Imprecise Data
SN - 978-989-758-555-5
AU - Brust C.
AU - Barz B.
AU - Denzler J.
PY - 2022
SP - 27
EP - 35
DO - 10.5220/0010766700003124
PB - SciTePress