UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning

2026-09-25

AI Summary

This study addresses the limitation in semantic reasoning for autism diagnosis caused by the scarcity of clinical text. To overcome this, we propose a multi-granularity prompt learning framework that leverages large multimodal models to generate hierarchical diagnostic descriptions, thereby compensating for missing clinical reports. Furthermore, we design a multi-scale alignment module based on a Mixture-of-Experts (MoE) network and vector-quantized prototypes to achieve precise multi-granular fusion of visual features and semantic information. Experimental results demonstrate that the proposed framework achieves accuracies of 75.9% and 91.6% on MRI and facial expression benchmarks, respectively, significantly outperforming existing methods while exhibiting strong robustness and interpretability.

Abstract

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder for which early and accurate diagnosis is critical to improving long-term developmental outcomes. However, existing ASD recognition methods are often constrained by the scarcity of diagnostic text data, forcing them to rely mainly on visual analysis and limiting their ability to model clinically meaningful semantic reasoning. To address this challenge, we propose UniAR, a unified framework enhanced by multi-granularity prompt learning for robust ASD recognition under heterogeneous data variations. Specifically, UniAR leverages a large multimodal model to generate hierarchical diagnostic descriptions at the word, phrase, and sentence levels, compensating for the lack of paired clinical reports. To align the generated semantics with visual evidence, we further design a Mixture-of-Experts-based Multi-Scale Alignment Module, which dynamically matches vector-quantized visual prototypes with semantic representations at corresponding granularities. Extensive experiments on four benchmarks covering brain MRI and facial expression scenarios show that UniAR consistently outperforms existing state-of-the-art methods, achieving average accuracies of 75.9\% on MRI benchmarks and 91.6\% on facial benchmarks, while improving average Accuracy on MRI benchmarks by 1.5 percentage points and average Accuracy on facial benchmarks by 1.2 percentage points over baselines. These results demonstrate that UniAR offers a robust and interpretable framework for ASD screening under semantic scarcity.

Problem

• Autism Spectrum Disorder
• diagnostic text scarcity
• semantic reasoning
• multimodal recognition

Innovation

• Multi-View Prompt Learning
• Large Multimodal Model
• Mixture-of-Experts
• Multi-Scale Alignment
• Autism Spectrum Disorder