用自监督学习提升蛋白定位模型在不同显微镜数据间的泛化能力
Generalization of Self-Supervised Vision Transformers for Protein Localization Across Microscopy Domains
- 用DINO预训练的视觉变换器提取跨域图像特征
- 医学图像预训练模型在开放细胞数据集上达0.8221的平均宏F1分数
- 小样本任务下仍表现优异，适合显微成像研究者使用
特定任务的显微镜数据集通常规模太小，难以训练出鲁棒的深度学习特征表示。自监督学习（SSL）可通过在大规模无标签数据上预训练缓解此问题，但其在不同染色协议和通道配置的显微镜领域间的表现仍不明确。本文研究了DINO预训练的视觉变换器在OpenCell数据集上进行蛋白定位的跨域迁移能力。采用三个DINO骨干网络——分别在ImageNet-1k、人类蛋白质图谱（HPA）和OpenCell上预训练——生成图像嵌入，并在OpenCell标签上训练监督分类头进行评估。所有预训练模型均表现出良好迁移性能，其中基于显微镜数据的HPA预训练模型表现最佳（平均宏F1分数 = 0.8221 ± 0.0062），略优于直接在OpenCell上训练的DINO模型（0.8057 ± 0.0090）。结果表明大规模预训练具有价值，且领域相关的自监督表示能有效泛化至相关但不同的显微镜数据集，即使标注数据有限也能实现强下游性能。
原文摘要 · Abstract (English)
Task-specific microscopy datasets are often too small to train deep learning models that learn robust feature representations. Self-supervised learning (SSL) can mitigate this by pretraining on large unlabeled datasets, but it remains unclear how well such representations transfer across microscopy domains with different staining protocols and channel configurations. We investigate the cross-domain transferability of DINO-pretrained Vision Transformers for protein localization on the OpenCell dataset. We generate image embeddings using three DINO backbones pretrained on ImageNet-1k, the Human Protein Atlas (HPA), and OpenCell, and evaluate them by training a supervised classification head on OpenCell labels. All pretrained models transfer well, with the microscopy-specific HPA-pretrained model achieving the best performance (mean macro $F_1$-score = 0.8221 $\pm$ 0.0062), slightly outperforming a DINO model trained directly on OpenCell (0.8057 $\pm$ 0.0090). These results highlight the value of large-scale pretraining and indicate that domain-relevant SSL representations can generalize effectively to related but distinct microscopy datasets, enabling strong downstream performance even when task-specific labeled data are limited.
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。