← Search

Mohammad Zalbagi Darestani

2 accepted papers

2022

Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing

ICML 2022spotlight

Deep learning based image reconstruction methods outperform traditional methods. However, neural networks suffer from a performance drop when applied to images from a different distribution than the training images. For example, a model trained for reconstructing knees in accelerated magnetic resona…

2021

Measuring Robustness in Deep Learning Based Compressive Sensing

ICML 2021oral

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive…