用自监督分割损失让重建模型在数据不全时仍能准确还原，适合无真值场景。
Equivariant Splitting: Self-supervised learning from incomplete data
- 设计新不变性定义，结合分割损失提升重建鲁棒性
- 在低秩前向模型下达到当前最优性能，图像修复等任务表现优异
- 特别适合无真值标注的医学成像与压缩感知任务
针对仅依赖噪声或不完整数据进行自监督学习的逆问题，本文提出一种新策略，适用于仅通过单一不完整观测模型获取测量数据的挑战性场景。我们引入重建网络中新的等变性定义，并证明自监督分割损失与等变重建网络的结合可得到无偏的监督损失估计。在图像修补、加速磁共振成像、稀疏视角计算机断层扫描及压缩感知等多个任务上实验表明，该方法在高度秩亏的前向模型设置下达到当前最优性能。代码已开源：https://github.com/vsechaud/Equivariant-Splitting。
原文摘要 · Abstract (English)
Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equivariance in the context of reconstruction networks, and show that the combination of self-supervised splitting losses and equivariant reconstruction networks results in unbiased estimates of the supervised loss. Through a series of experiments on image inpainting, accelerated magnetic resonance imaging, sparse-view computed tomography, and compressive sensing, we demonstrate that the proposed loss achieves state-of-the-art performance in settings with highly rank-deficient forward models. The code is available at https://github.com/vsechaud/Equivariant-Splitting
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。