A Review of Emerging Research Directions in Abstract Visual Reasoning
arXiv:2202.10284 · doi:10.1016/j.inffus.2022.11.011
Abstract
Abstract Visual Reasoning (AVR) problems are commonly used to approximate human intelligence. They test the ability of applying previously gained knowledge, experience and skills in a completely new setting, which makes them particularly well-suited for this task. Recently, the AVR problems have become popular as a proxy to study machine intelligence, which has led to emergence of new distinct types of problems and multiple benchmark sets. In this work we review this emerging AVR research and propose a taxonomy to categorise the AVR tasks along 5 dimensions: input shapes, hidden rules, target task, cognitive function, and main challenge. The perspective taken in this survey allows to characterise AVR problems with respect to their shared and distinct properties, provides a unified view on the existing approaches for solving AVR tasks, shows how the AVR problems relate to practical applications, and outlines promising directions for future work. One of them refers to the observation that in the machine learning literature different tasks are considered in isolation, which is in the stark contrast with the way the AVR tasks are used to measure human intelligence, where multiple types of problems are combined within a single IQ test.
References in corpus (20)
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Diffusion Models in Vision: A Survey
- The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
- Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
- Visual Entailment: A Novel Task for Fine-Grained Image Understanding
- Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
- Abstraction and Analogy-Making in Artificial Intelligence
- Neurosymbolic AI: The 3rd Wave
- Five Points to Check when Comparing Visual Perception in Humans and Machines
- Multi-Label Contrastive Learning for Abstract Visual Reasoning
- Learning to Discover Efficient Mathematical Identities
- The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning
- Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
- Solving the Same-Different Task with Convolutional Neural Networks
- Few-shot Visual Reasoning with Meta-analogical Contrastive Learning
- Differentiable Logic Machines
- Dynamic Inference with Neural Interpreters
- Visual analogy: Deep learning versus compositional models
- Few-Shot Abstract Visual Reasoning With Spectral Features
- Odd-One-Out Representation Learning