Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography
This work addresses the challenge of minimizing X-ray doses and measurement times in scientific CT, offering a domain-specific solution that is incremental in its combination of existing techniques.
The paper tackles the problem of reducing data acquisition requirements in computed tomography by introducing Diffusion Active Learning, which combines generative diffusion modeling with sequential experimental design, resulting in substantial reductions in data needs and improved image reconstruction quality across real-world datasets.
We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on scientific computed tomography (CT) for experimental validation, where structured prior datasets are available, and reducing data requirements directly translates to shorter measurement times and lower X-ray doses. We first pre-train an unconditional diffusion model on domain-specific CT reconstructions. The diffusion model acts as a learned prior that is data-dependent and captures the structure of the underlying data distribution, which is then used in two ways: It drives the active learning process and also improves the quality of the reconstructions. During the active learning loop, we employ a variant of diffusion posterior sampling to generate conditional data samples from the posterior distribution, ensuring consistency with the current measurements. Using these samples, we quantify the uncertainty in the current estimate to select the most informative next measurement. Our results show substantial reductions in data acquisition requirements, corresponding to lower X-ray doses, while simultaneously improving image reconstruction quality across multiple real-world tomography datasets.