Affinity-VAE：在科学图像的表示学习中融入先验知识
Affinity-VAE: incorporating prior knowledge in representation learning from scientific images
AI总结：
本文提出 Affinity-VAE，通过实例相似性先验约束科学图像表示学习，在 cryo-ET 蛋白质数据上实现旋转不变聚类、姿态与结构解耦及可解释潜在空间。
摘要：
学习紧凑且可解释的数据表示是科学图像分析中的一项关键挑战。本文提出 Affinity-VAE，这是一种生成模型，使我们能够在训练期间将关于数据集中实例相似性的科学直觉施加到所学表示上。我们在冷冻电子断层扫描（cryo-ET）这一科学领域展示了该方法的效用；在该领域中，当前的一项重大挑战是在有噪声、低对比度的断层扫描图像体中识别相似分子。该任务不同于分类，因为在推理时，某个实例是否属于训练集是未知的。我们利用蛋白质结构的先验知识训练 Affinity-VAE，以引导潜在空间。我们的模型能够在潜在表示中形成旋转不变、形态同质的簇，并且与其他方法相比具有更好的簇分离度。它在蛋白质分类上取得了具有竞争力的性能，同时还带来了解耦物体姿态、结构相似性以及可解释潜在表示的额外优势。在 cryo-ET 数据背景下，Affinity-VAE 可捕获所识别蛋白质在三维空间中的取向，该取向可用作后续科学实验的先验。在真值训练集并不总是可行的科学成像中，从训练后的网络中提取物理原理具有重要意义。
英文摘要：
Learning compact and interpretable representations of data is a critical challenge in scientific image analysis. Here, we introduce Affinity-VAE, a generative model that enables us to impose our scientific intuition about the similarity of instances in the dataset on the learned representation during training. We demonstrate the utility of the approach in the scientific domain of cryo-electron tomography (cryo-ET) where a significant current challenge is to identify similar molecules within a noisy and low contrast tomographic image volume. This task is distinct from classification in that, at inference time, it is unknown whether an instance is part of the training set or not. We trained affinity-VAE using prior knowledge of protein structure to inform the latent space. Our model is able to create rotationally-invariant, morphologically homogeneous clusters in the latent representation, with improved cluster separation compared to other approaches. It achieves competitive performance on protein classification with the added benefit of disentangling object pose, structural similarity and an interpretable latent representation. In the context of cryo-ET data, affinity-VAE captures the orientation of identified proteins in 3D which can be used as a prior for subsequent scientific experiments. Extracting physical principles from a trained network is of significant importance in scientific imaging where a ground truth training set is not always feasible.
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。
