TY - JOUR
T1 - Parameter-Efficient Adaptation for Computational Imaging
AU - Yismaw, Nebiyou
AU - Kamilov, Ulugbek S.
AU - Salman Asif, M.
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Deep learning-based methods provide remarkable performance in a number of computational imaging problems. Examples include end-to-end trained networks that map measurements to unknown signals, plug-and-play (PnP) methods that use pretrained denoisers as image prior, and model-based unrolled networks that train artifact removal blocks. Many of these methods lack robustness and fail to generalize with distribution shifts in data, measurements, and noise. In this paper, we present a simple framework to perform domain adaptation as data and measurement distribution shifts. Our method learns a small number of factors to add in a pretrained model to bridge the gap in performance. We present a number of experiments on accelerated magnetic resonance imaging (MRI) reconstruction and image deblurring to demonstrate that our method requires a small amount of memory and parameter overhead to adapt to new domains.
AB - Deep learning-based methods provide remarkable performance in a number of computational imaging problems. Examples include end-to-end trained networks that map measurements to unknown signals, plug-and-play (PnP) methods that use pretrained denoisers as image prior, and model-based unrolled networks that train artifact removal blocks. Many of these methods lack robustness and fail to generalize with distribution shifts in data, measurements, and noise. In this paper, we present a simple framework to perform domain adaptation as data and measurement distribution shifts. Our method learns a small number of factors to add in a pretrained model to bridge the gap in performance. We present a number of experiments on accelerated magnetic resonance imaging (MRI) reconstruction and image deblurring to demonstrate that our method requires a small amount of memory and parameter overhead to adapt to new domains.
UR - http://www.scopus.com/inward/record.url?scp=105001594905&partnerID=8YFLogxK
U2 - 10.1109/ICASSP48485.2024.10447475
DO - 10.1109/ICASSP48485.2024.10447475
M3 - Conference article
AN - SCOPUS:105001594905
SN - 1520-6149
SP - 13051
EP - 13055
JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
T2 - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -