SVD-DIP: Overcoming the Overfitting Problem in DIP-based CT Reconstruction
Not on the map. Why?
Abstract (arXiv)
The deep image prior (DIP) is a well-established unsupervised deep learning method for image reconstruction; yet it is far from being flawless. The DIP overfits to noise if not early stopped, or optimized via a regularized objective. We build on the regularized fine-tuning of a pretrained DIP, by adopting a novel strategy that restricts the learning to the adaptation of singular values. The proposed SVD-DIP uses ad hoc convolutional layers whose pretrained parameters are decomposed via the singular value decomposition. Optimizing the DIP then solely consists in the fine-tuning of the singular values, while keeping the left and right singular vectors fixed. We thoroughly validate the proposed method on real-measured μCT data of a lotus root as well as two medical datasets (LoDoPaB and Mayo). We report significantly improved stability of the DIP optimization, by overcoming the overfitting to noise.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 28 Mar 2023.
Builds on
16 of 29 references.
References · 16
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2017Deep Image Priorcited by 1,097
- 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
- 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
- 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
- 2018Image Restoration using Total Variation Regularized Deep Image Priorcited by 65
- 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
- 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
- 2018Unsupervised Learning with Stein's Unbiased Risk Estimatorcited by 47
- 2021Early Stopping for Deep Image Priorcited by 44
- 2021Rethinking Deep Image Prior for Denoisingcited by 38
- 2021On Measuring and Controlling the Spectral Bias of the Deep Image Priorcited by 36
4 more
- 2018Regularization by architecture: A deep prior approach for inverse problemscited by 26
- 2021An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstructioncited by 16
- 2020ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithmscited by 13
- 2021Image Restoration by Deep Projected GSUREcited by 8
Built on by
Citing papers per year: 2023: 2.
2 papers.