Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
ACM Computing Surveys · 31.07.2025 · 57 (7) · 1-36
DOI: 10.1145/3715093 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 21.02.2025. Verfasst von Mikołaj Małkiński und 1 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 186 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Warsaw University of Technology within the Excellence Initiative: Research University (IDUB) programme.
Abstract (Originalsprache)
visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a “natural” way, even without prior experience, this type of problem has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks—the Raven’s Progressive Matrices (RPMs)—and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as present the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We also attempt to put RPM studies in a more general perspective and demonstrate how real-world problems from the outside of AVR area can benefit from the presented research.
Förderung
- Warsaw University of Technology within the Excellence Initiative: Research University (IDUB) programme
Zitieren
APA
Małkiński, M., & Mańdziuk, J. (2025). Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices. ACM Computing Surveys, 57(7), 1-36. https://doi.org/10.1145/3715093
Vancouver
Małkiński M, Mańdziuk J. Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices. ACM Computing Surveys. 2025;57(7):1-36. doi:10.1145/3715093
BibTeX
@article{Makiski2025,
author = {Małkiński, Mikołaj and Mańdziuk, Jacek},
title = {Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {7},
pages = {1--36},
doi = {10.1145/3715093}
}
EUVIMED