Pith. sign in

REVIEW 3 cited by

Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.12382 v2 pith:5GOM7TTJ submitted 2022-01-28 cs.AI cs.CVcs.LG

classification cs.AIcs.CVcs.LG
keywords learningproblemsdeepmethodsrpmssolvingabstractcurrent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Abstract 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 problems 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, 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 conclude the paper by demonstrating how real-world problems can benefit from the discoveries of RPM studies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models

    cs.AI 2025-02 conditional novelty 6.0 of 10

    The MM-IQ benchmark shows state-of-the-art multimodal models score 33% on abstract visual reasoning puzzles versus 25% chance and 51% for humans.

  2. Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A single conditional generative model, trained only on RPM-style puzzles, can be repurposed via probability scoring to solve odd-one-out, analogy, and categorization tasks, with modest zero-shot transfer.

  3. Learning Visual Abstract Reasoning through Dual-Stream Networks

    cs.CV 2024-11 conditional novelty 5.0 of 10

    A dual-stream network combining CNN and vision transformer features, followed by a rule extractor, achieves state-of-the-art accuracy on multiple Raven's Progressive Matrices benchmarks, including large gains on out-o...

Pith tools