掩码自编码器是可扩展的细胞形态学习器
Masked Autoencoders are Scalable Learners of Cellular Morphology
AI总结：
本文研究自监督掩码自编码器在细胞形态学图像上的可扩展性，证明CNN和ViT架构在大规模显微镜数据上训练后显著优于弱监督基线，其中ViT-L/8在推断已知生物学关系时相对提升高达28%。
摘要：
在高内涵显微镜筛选中从细胞表型推断生物学关系，为生物学研究带来了重大机遇与挑战。已有结果表明，深度视觉模型比手工设计的特征能更好地捕获生物信号。本文探索了自监督深度学习方法在更大显微镜数据集上训练更大模型时的扩展能力。我们的结果表明，基于CNN和ViT的掩码自编码器均显著优于弱监督基线。在我们规模的高端，一个在从9300万张显微镜图像中采样的超过35亿个独特裁剪块上训练的ViT-L/8，在推断从公共数据库整理的已知生物学关系时，相对于我们最佳的弱监督基线实现了高达28%的相对提升。本工作发布的相关代码和部分模型可在以下地址获取：https://github.com/recursionpharma/maes_microscopy。
英文摘要：
Inferring biological relationships from cellular phenotypes in high-content microscopy screens provides significant opportunity and challenge in biological research. Prior results have shown that deep vision models can capture biological signal better than hand-crafted features. This work explores how self-supervised deep learning approaches scale when training larger models on larger microscopy datasets. Our results show that both CNN- and ViT-based masked autoencoders significantly outperform weakly supervised baselines. At the high-end of our scale, a ViT-L/8 trained on over 3.5-billion unique crops sampled from 93-million microscopy images achieves relative improvements as high as 28% over our best weakly supervised baseline at inferring known biological relationships curated from public databases. Relevant code and select models released with this work can be found at: https://github.com/recursionpharma/maes_microscopy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
