通过一致性视图对齐，提升3D医学图像分割的预训练效果
Consistent View Alignment Improves Foundation Models for 3D Medical Image Segmentation
- 设计视图对齐机制，融合多视角互补信息
- 在MICCAI 2025挑战中分别获第一、二名
- 适用于需要高质量3D医学表征的下游任务
当前表示学习方法通常假设数据点的不相关视图足以学习有意义的表示。本文挑战这一假设，证明潜在空间中的有意义结构不会自然出现，必须显式引入。提出一致视图对齐方法，通过对齐不同视图的表示来整合互补信息，同时避免引入虚假正例。实验表明，该自监督学习方法显著提升下游任务性能，凸显结构化视图对齐的重要性。在使用Primus视觉变压器和ResEnc卷积网络时，本方法在MICCAI 2025 SSL3D挑战赛中分别获得第一名和第二名。代码与预训练权重已公开于https://github.com/Tenbatsu24/LatentCampus。
原文摘要 · Abstract (English)
Many recent approaches in representation learning implicitly assume that uncorrelated views of a data point are sufficient to learn meaningful representations for various downstream tasks. In this work, we challenge this assumption and demonstrate that meaningful structure in the latent space does not emerge naturally. Instead, it must be explicitly induced. We propose a method that aligns representations from different views of the data to align complementary information without inducing false positives. Our experiments show that our proposed self-supervised learning method, Consistent View Alignment, improves performance for downstream tasks, highlighting the critical role of structured view alignment in learning effective representations. Our method achieved first and second place in the MICCAI 2025 SSL3D challenge when using a Primus vision transformer and ResEnc convolutional neural network, respectively. The code and pretrained model weights are released at https://github.com/Tenbatsu24/LatentCampus.
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。