A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processing
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.
Code (1)
Tasks
Inductive BiasSimilar Papers 제목 키워드 기반
Cognitively-Inspired Tokens Overcome Egocentric Bias in Multimodal Models
Multimodal language models (MLMs) perform well on semantic vision-language tasks but fail at spatial reasoning that requires adopting another agent's visual perspective. These errors reflect a persistent egocentric bias …
Spatial ReasoningMind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's E…
Vector Symbolic Algebras for the Abstraction and Reasoning Corpus
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for ev…
Program SynthesisFrom Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and Reliable LLM Reasoning
Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a funda…
Reinforcement LearningLearning Visual Abstract Reasoning through Dual-Stream Networks
Visual abstract reasoning tasks present challenges for deep neural networks, exposing limitations in their capabilities. In this work, we present a neural network model that addresses the challenges posed by Raven's Prog…
Visual Reasoning