Timezone: »

Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
Anastasios Angelopoulos · Amit Pal Kohli · Stephen Bates · Michael Jordan · Jitendra Malik · Thayer Alshaabi · Srigokul Upadhyayula · Yaniv Romano

Tue Jul 19 11:00 AM -- 11:05 AM (PDT) @ Room 318 - 320

Image-to-image regression is an important learning task, used frequently in biological imaging. Current algorithms, however, do not generally offer statistical guarantees that protect against a model's mistakes and hallucinations. To address this, we develop uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems. In particular, we show how to derive uncertainty intervals around each pixel that are guaranteed to contain the true value with a user-specified confidence probability. Our methods work in conjunction with any base machine learning model, such as a neural network, and endow it with formal mathematical guarantees—regardless of the true unknown data distribution or choice of model. Furthermore, they are simple to implement and computationally inexpensive. We evaluate our procedure on three image-to-image regression tasks: quantitative phase microscopy, accelerated magnetic resonance imaging, and super-resolution transmission electron microscopy of a Drosophila melanogaster brain.

Author Information

Anastasios Angelopoulos (UC Berkeley)
Amit Pal Kohli (UC Berkeley)
Stephen Bates (University of California, Berkeley)
Michael Jordan (UC Berkeley)
Jitendra Malik (University of California at Berkeley)
Thayer Alshaabi (University of California, Berkeley)
Srigokul Upadhyayula (University of California, Berkeley)
Yaniv Romano (Technion---Israel Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors