Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processing (2309.10532v3)

Published 19 Sep 2023 in cs.AI

Abstract: We introduce a new neural architecture for solving visual abstract reasoning tasks inspired by human cognition, specifically by observations that human abstract reasoning often interleaves perceptual and conceptual processing as part of a flexible, iterative, and dynamic cognitive process. Inspired by this principle, our architecture models visual abstract reasoning as an iterative, self-contrasting learning process that pursues consistency between perceptual and conceptual processing of visual stimuli. We explain how this new Contrastive Perceptual-Conceptual Network (CPCNet) works using matrix reasoning problems in the style of the well-known Raven's Progressive Matrices intelligence test. Experiments on the machine learning dataset RAVEN show that CPCNet achieves higher accuracy than all previously published models while also using the weakest inductive bias. We also point out a substantial and previously unremarked class imbalance in the original RAVEN dataset, and we propose a new variant of RAVEN -- AB-RAVEN -- that is more balanced in terms of abstract concepts.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Measuring abstract reasoning in neural networks. In International conference on machine learning, 511–520. PMLR.
  2. Barsalou, L. W. L. W. 1999. Perceptual symbol systems. Behavioral and Brain Sciences, 22(4): 612–613.
  3. Scale-localized abstract reasoning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12557–12565.
  4. What one intelligence test measures: a theoretical account of the processing in the Raven Progressive Matrices Test. Psychological review, 97(3): 404.
  5. Dorolle, M. 1949. Le Raisonnement Par Analogie. Paris: PUF.
  6. Evans, T. G. 1964. A program for the solution of a class of geometric-analogy intelligence-test questions. Technical report, AIR FORCE CAMBRIDGE RESEARCH LABS LG HANSCOM FIELD MASS.
  7. Gentner, D. 1983. Structure-Mapping: A Theoretical Framework for Analogy. Cognitive Science, 7(2): 155–170.
  8. Attention on abstract visual reasoning. arXiv preprint arXiv:1911.05990.
  9. Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction. arXiv preprint arXiv:2111.12301.
  10. A neuro-vector-symbolic architecture for solving Raven’s progressive matrices. Nature Machine Intelligence.
  11. Surfaces and essences: Analogy as the fuel and fire of thinking. Basic books.
  12. Stratified Rule-Aware Network for Abstract Visual Reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 1567–1574.
  13. Hunt, E. 2010. Human Intelligence. Cambridge University Press.
  14. Solving raven’s progressive matrices with multi-layer relation networks. In International Joint Conference on Neural Networks. IEEE.
  15. Supervised Contrastive Learning. In Larochelle, H.; Ranzato, M.; Hadsell, R.; Balcan, M.; and Lin, H., eds., Advances in Neural Information Processing Systems, volume 33, 18661–18673. Curran Associates, Inc.
  16. The case for mental imagery. New York, NY: Oxford University Press, 1st. edition.
  17. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, NIPS’12, 1097–1105. Red Hook, NY, USA: Curran Associates Inc.
  18. A computational model for solving problems from the Raven’s Progressive Matrices intelligence test using iconic visual representations. Cognitive Systems Research, 22: 47–66.
  19. Modeling visual problem solving as analogical reasoning. Psychological review, 124(1): 60.
  20. Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven’s Progressive Matrices. arXiv preprint arXiv:2201.12382.
  21. A review of emerging research directions in Abstract Visual Reasoning. Information Fusion.
  22. Fractals and ravens. Artificial Intelligence, 215: 1–23.
  23. Raven, J. 2008. The Raven progressive matrices tests: their theoretical basis and measurement model.
  24. Raven, J. C. 1936. Mental tests used in genetic studies: The performance of related individuals on tests mainly educative and mainly reproductive. Unpublished master’s thesis, University of London.
  25. SAViR-T: Spatially Attentive Visual Reasoning with Transformers. In Amini, M.-R.; Canu, S.; Fischer, A.; Guns, T.; Kralj Novak, P.; and Tsoumakas, G., eds., Machine Learning and Knowledge Discovery in Databases, 460–476. Cham: Springer Nature Switzerland. ISBN 978-3-031-26409-2.
  26. Raven’s Progressive Matrices Completion with Latent Gaussian Process Priors. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 9612–9620.
  27. The topography of ability and learning correlations. Advances in the psychology of human intelligence, 2(S 47): 103.
  28. A closer look at generalisation in raven. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVII 16, 601–616. Springer.
  29. Abstract Diagrammatic Reasoning with Multiplex Graph Networks. In International Conference on Learning Representations 2020.
  30. Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability. arXiv:2210.14914.
  31. The scattering compositional learner: Discovering objects, attributes, relationships in analogical reasoning. arXiv preprint arXiv:2007.04212.
  32. Abstract Visual Reasoning: An Algebraic Approach for Solving Raven’s Progressive Matrices. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6715–6724.
  33. Not quite any way you slice it: How different analogical constructions affect Raven’s Matrices performance. In Proceedings of the Eighth Annual Conference on Advances in Cognitive Systems (ACS).
  34. A Conceptual Chronicle of Solving Raven’s Progressive Matrices Computationally. In CEUR Workshop Proceedings.
  35. Abstract Reasoning via Logic-guided Generation. arXiv preprint arXiv:2107.10493.
  36. Raven: A dataset for relational and analogical visual reasoning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5317–5327.
  37. Learning perceptual inference by contrasting. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, volume 32.
  38. Abstract spatial-temporal reasoning via probabilistic abduction and execution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9736–9746.
  39. Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning. In Proceedings of the European Conference on Computer Vision (ECCV).
  40. Abstract reasoning with distracting features. Advances in Neural Information Processing Systems, 32.
  41. Unsupervised Abstract Reasoning for Raven’s Problem Matrices. IEEE Transactions on Image Processing, 30: 8332–8341.
  42. Effective abstract reasoning with dual-contrast network. In International Conference on Learning Representations.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Yuan Yang (60 papers)
  2. Deepayan Sanyal (6 papers)
  3. James Ainooson (8 papers)
  4. Joel Michelson (6 papers)
  5. Effat Farhana (4 papers)
  6. Maithilee Kunda (15 papers)
Citations (2)
View on Semantic Scholar