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

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.

References in corpus (20)

• Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
• A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input
• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• Self-supervised Pretraining of Visual Features in the Wild
• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
• Abstraction and Analogy-Making in Artificial Intelligence
• Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering
• The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning
• The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain
• A Review of Emerging Research Directions in Abstract Visual Reasoning
• Emergent Analogical Reasoning in Large Language Models
• Solving Raven's Progressive Matrices with Neural Networks
• PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning
• Few-shot Visual Reasoning with Meta-analogical Contrastive Learning
• Dynamic Inference with Neural Interpreters
• Visual analogy: Deep learning versus compositional models
• Evaluating Understanding on Conceptual Abstraction Benchmarks
• Systematic Visual Reasoning through Object-Centric Relational Abstraction