TY - GEN
T1 - Robustness of Deep Equilibrium Architectures to Changes in the Measurement Model
AU - Hu, Junhao
AU - Shoushtari, Shirin
AU - Zou, Zihao
AU - Liu, Jiaming
AU - Sun, Zhixin
AU - Kamilov, Ulugbek S.
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Deep model-based architectures (DMBAs) are widely used in imaging inverse problems to integrate physical measurement models and learned image priors. Plug-and-play priors (PnP) and deep equilibrium models (DEQ) are two DMBA frameworks that have received significant attention. The key difference between the two is that the image prior in DEQ is trained by using a specific measurement model, while that in PnP is trained as a general image denoiser. This difference is behind a common assumption that PnP is more robust to changes in the measurement models compared to DEQ. This paper investigates the robustness of DEQ priors to changes in the measurement models. Our results on two imaging inverse problems suggest that DEQ priors trained under mismatched measurement models outperform image denoisers.
AB - Deep model-based architectures (DMBAs) are widely used in imaging inverse problems to integrate physical measurement models and learned image priors. Plug-and-play priors (PnP) and deep equilibrium models (DEQ) are two DMBA frameworks that have received significant attention. The key difference between the two is that the image prior in DEQ is trained by using a specific measurement model, while that in PnP is trained as a general image denoiser. This difference is behind a common assumption that PnP is more robust to changes in the measurement models compared to DEQ. This paper investigates the robustness of DEQ priors to changes in the measurement models. Our results on two imaging inverse problems suggest that DEQ priors trained under mismatched measurement models outperform image denoisers.
KW - Computational imaging
KW - deep equilibrium models
KW - inverse problems
KW - plug-and-play priors
UR - https://www.scopus.com/pages/publications/86000387837
U2 - 10.1109/ICASSP49357.2023.10096199
DO - 10.1109/ICASSP49357.2023.10096199
M3 - Conference contribution
AN - SCOPUS:86000387837
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Y2 - 4 June 2023 through 10 June 2023
ER -