Understanding the computational demands underlying visual reasoning

Abstract

Visual understanding requires comprehending complex visual relations between objects within a scene. Here, we seek to characterize the computational demands for abstract visual reasoning. We do this by systematically assessing the ability of modern deep convolutional neural networks (CNNs) to learn to solve the "Synthetic Visual Reasoning Test" (SVRT) challenge, a collection of twenty-three visual reasoning problems. Our analysis reveals a novel taxonomy of visual reasoning tasks, which can be primarily explained by both the type of relations (same-different vs. spatial-relation judgments) and the number of relations used to compose the underlying rules. Prior cognitive neuroscience work suggests that attention plays a key role in humans' visual reasoning ability. To test this hypothesis, we extended the CNNs with spatial and feature-based attention mechanisms. In a second series of experiments, we evaluated the ability of these attention networks to learn to solve the SVRT challenge and found the resulting architectures to be much more efficient at solving the hardest of these visual reasoning tasks. Most importantly, the corresponding improvements on individual tasks partially explained our novel taxonomy. Overall, this work provides an granular computational account of visual reasoning and yields testable neuroscience predictions regarding the differential need for feature-based vs. spatial attention depending on the type of visual reasoning problem.

26 pages, 16 figures

References in corpus (8)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• MLP-Mixer: An all-MLP Architecture for Vision
• On the Binding Problem in Artificial Neural Networks
• Solving the Same-Different Task with Convolutional Neural Networks
• Recurrent neural circuits for contour detection
• Do Neural Networks for Segmentation Understand Insideness?
• Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test

Cited by in corpus (2)

• Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach
• Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning