轻量级多模态模型让手机端牙科影像智能分析更高效隐私。
Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language Models
- 用小模型轻量化适配，实现手机端高效牙科图像理解
- 20亿参数模型在手机上处理单张图像仅需4.31秒，提速4.9倍
- 适合基层医疗、隐私敏感场景的本地化牙科筛查应用
牙科视觉语言模型的评估仍分散于不同数据集、任务定义和指标，且常忽略计算开销。这限制了其在专科中心外的广泛应用，而及时推理、硬件受限及本地化处理患者图像对临床预筛至关重要。本文提出Pocket-Dentist，一个面向牙科多模态问答的高效性基准，整合了来自BRAR和MetaDent的约1,159名患者的三个数据集、五种任务类型和七项指标。在14个典型VLM上评估发现：经轻量适配后，20亿参数的小型模型在多数指标上可媲美更大模型，但计算成本显著更低。部署于iPhone 17 Pro时，微调后的Pocket-Dentist-2B模型单样本处理耗时4.31秒，相比70亿参数基线降低4.9倍延迟、节省2.3倍内存。
原文摘要 · Abstract (English)
Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cost. This limits their widespread deployment for dental screening outside specialist centres, where timely inference, limited hardware, and local handling of patient images are vital for practical, privacy-preserving clinical prescreening. Here we present Pocket-Dentist, an efficiency-aware benchmark for dental multimodal question answering that brings together three datasets spanning approximately 1,159 patients from BRAR and MetaDent, five task types and seven metrics. Across 14 typical VLMs, our results reveal an interesting observation: compact VLMs, such as 2B-parameter models, become competitive with much larger VLMs on most metrics after lightweight adaptation while requiring substantially lower computational costs in dental image understanding. Deployed locally on an iPhone 17 Pro, our finetuned compact VLM Pocket-Dentist-2B processed each sample in 4.31 s, reducing latency by 4.9x and memory use by 2.3x compared with a 7B baseline. Our project page is available at https://2026-icml.github.io/pocket-dentist-icml.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。