mlsanityData to 7 Oct 2026

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

arXiv 2201.12382 ↗First posted 28 Jan 2022cs.AI cs.CV cs.LGcited by 37

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

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.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 101 of its 195 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

101 of 195 references.

References · 101

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2015VQA: Visual Question Answeringcited by 2,489
38 more
  1. 2017Non-local Neural Networkscited by 2,290
  2. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  3. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  4. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  5. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  6. 2020Object-Centric Learning with Slot Attentioncited by 865
  7. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  8. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  10. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
  11. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  12. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  13. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  14. 2017Generative Adversarial Networks: An Overviewcited by 588
  15. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  16. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  17. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  18. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 475
  19. 2018Spherical CNNscited by 452
  20. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  21. 2017A simple neural network module for relational reasoningcited by 345
  22. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 337
  23. 2018Understanding disentangling in β-VAEcited by 332
  24. 2015Towards AI-Complete Question Answering: A Set of Prerequisite Toy Taskscited by 309
  25. 2017Relation Networks for Object Detectioncited by 305
  26. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  27. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
  28. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  29. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 225
  30. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  31. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  32. 2019Contrastive Learning of Structured World Modelscited by 206
  33. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
  34. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 197
  35. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  36. 2019SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercited by 173
  37. 2018Measuring abstract reasoning in neural networkscited by 165
  38. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 141

50 most cited of 101 All 101 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 10; 2024: 12; 2025: 9; 2026: 3.

37 papers.

Sort:

By area:

  1. 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 97
  2. 2022A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matricescited by 64
  3. 2023Large Language Models are Visual Reasoning Coordinatorscited by 58
  4. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Modelscited by 37
  5. 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
  6. 2024What is the Visual Cognition Gap between Humans and Multimodal LLMs?cited by 30
  7. 2025MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Modelscited by 28
  8. 2025Explain Before You Answer: A Survey on Compositional Visual Reasoningcited by 26
  9. 2023In-Context Analogical Reasoning with Pre-Trained Language Modelscited by 22
  10. 2022Multimodal Analogical Reasoning over Knowledge Graphscited by 21
  11. 2025Perception in Reflectioncited by 13
  12. 2024Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architecturescited by 9
25 more
  1. 2024Towards Learning Abductive Reasoning using VSA Distributed Representationscited by 9
  2. 2025Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problemscited by 7
  3. 2023Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problemscited by 6
  4. 2023One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problemscited by 6
  5. 2024Text-to-Image Cross-Modal Generation: A Systematic Reviewcited by 5
  6. 2025Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?cited by 5
  7. 2023A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processingcited by 4
  8. 2023A Survey on Image-text Multimodal Modelscited by 4
  9. 2024Sandra -- A Neuro-Symbolic Reasoner Based On Descriptions And Situationscited by 4
  10. 2024A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoningcited by 4
  11. 2024Learning Visual Abstract Reasoning through Dual-Stream Networkscited by 4
  12. 2025I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Modelscited by 4
  13. 2026Toward Cognitive Supersensing in Multimodal Large Language Modelcited by 4
  14. 2025Unraveling the geometry of visual relational reasoningcited by 3
  15. 2024Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selectioncited by 2
  16. 2024Can Multimodal Large Language Model Think Analogically?cited by 2
  17. 2023Learning Abstract Visual Reasoning via Task Decomposition: A Case Study in Raven Progressive Matricescited by 1
  18. 2024Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoningcited by 1
  19. 2024A Unified View of Abstract Visual Reasoning Problemscited by 1
  20. 2023Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Taskscited by 0
  21. 2024A Neural Model of Rule Discovery with Relatively Short-Term Sequence Memorycited by 0
  22. 2025Advancing Generalization Across a Variety of Abstract Visual Reasoning Taskscited by 0
  23. 2025Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoningcited by 0
  24. 2026Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Modelscited by 0
  25. 2026ChronoVision: Temporal Reasoning via Latent State Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Learning to reason over visual objects
  2. 2025On Data Synthesis and Post-training for Visual Abstract Reasoning
  3. 2024How Far Are We from Intelligent Visual Deductive Reasoning?
  4. 2022SAViR-T: Spatially Attentive Visual Reasoning with Transformers
  5. 2024ViTCN: Vision Transformer Contrastive Network For Reasoning
  6. 2022Visual-Imagery-Based Analogical Construction in Geometric Matrix Reasoning Task
  7. 2024Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach
  8. 2022A Benchmark for Compositional Visual Reasoning