arXiv：cs.AI· Jiaqi Tang, Yu Wang, Yang Liu, Jing Tao, Fandong Zhang, Zhou Zhen, Xiahai Zhuang, Qingchao Chen, Yining Yang, Yizhou Yu·· 5 小时前
3D 医学视觉基础模型基准测试与可迁移性估计
Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
AI 导读
研究对 23 个自监督 3D 医学基础模型在相同的 14 个分割、分类与回归任务上进行了基准测试，发现没有任何候选模型能在所有分割任务或所有分类回归任务中稳居前三，卷积编码器与 Transformer 的表现因任务而异。
正文
Abstract:Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols. Models also differ in architecture, pretraining objective and data, while downstream targets range from voxel-level masks to patient-level diagnoses and outcomes. As a result, published findings provide little directly comparable evidence for choosing a model for a new task. Direct comparison of adaptation performance requires fine-tuning candidates on labelled target data, at substantial computational cost. We benchmark 23 candidates across the same 14 segmentation, classification and regression tasks spanning multiple anatomies and modalities. No candidate ranked among the top three across all segmentation tasks or across all classification and regression tasks; a convolutional encoder could outperform a transformer trained with the same objective on one task but underperform it on another. We benchmark transferability estimators against the fine-tuned rankings and find that their agreement varies across dense segmentation, classification and regression. InsightRank uses task-appropriate frozen-feature statistics and architecture-aware pairwise comparisons to rank candidates before fine-tuning. Across the 23-model pool, mean Kendall tau-b was 0.431 for segmentation and 0.352 for classification and regression. The segmentation Top 3 contained a task winner on four of nine tasks; the image-level Top 3 contained none on the five tasks, despite better full-ranking agreement than the matched conventional estimators. A three-model shortlist reduced recorded extraction-plus-training job time by 85.8% across seven segmentation tasks. Together, the benchmark provides a common reference for model selection and InsightRank offers a lower-cost way to prioritize fine-tuning, with shortlist performance that differs by target type.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17573 [cs.CV] |
| (or arXiv:2610.17573v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17573 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiaqi Tang [view email]
[v1]
Tue, 13 Oct 2026 01:52:19 UTC (1,884 KB)
来源：arXiv：cs.AI · arxiv.org