UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

• URL: http://arxiv.org/abs/2505.11720v1
• Date: Fri, 16 May 2025 22:05:28 GMT
• Title: UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights
• Authors: Shijun Liang, Ismail R. Alkhouri, Siddhant Gautam, Qing Qu, Saiprasad Ravishankar,
• Abstract summary: UGoDIT is designed for the low-data regime where only a very small number, M, of sub-sampled measurement vectors are available during training.<n>Our method learns a set of transferable weights by optimizing a shared encoder and M disentangled decoders.<n>We evaluate UGoDIT on both medical (multi-coil MRI) and natural (super resolution and non-linear deblurring) image recovery tasks.
• Score: 10.447347462729462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in data-centric deep generative models have led to significant progress in solving inverse imaging problems. However, these models (e.g., diffusion models (DMs)) typically require large amounts of fully sampled (clean) training data, which is often impractical in medical and scientific settings such as dynamic imaging. On the other hand, training-data-free approaches like the Deep Image Prior (DIP) do not require clean ground-truth images but suffer from noise overfitting and can be computationally expensive as the network parameters need to be optimized for each measurement set independently. Moreover, DIP-based methods often overlook the potential of learning a prior using a small number of sub-sampled measurements (or degraded images) available during training. In this paper, we propose UGoDIT, an Unsupervised Group DIP via Transferable weights, designed for the low-data regime where only a very small number, M, of sub-sampled measurement vectors are available during training. Our method learns a set of transferable weights by optimizing a shared encoder and M disentangled decoders. At test time, we reconstruct the unseen degraded image using a DIP network, where part of the parameters are fixed to the learned weights, while the remaining are optimized to enforce measurement consistency. We evaluate UGoDIT on both medical (multi-coil MRI) and natural (super resolution and non-linear deblurring) image recovery tasks under various settings. Compared to recent standalone DIP methods, UGoDIT provides accelerated convergence and notable improvement in reconstruction quality. Furthermore, our method achieves performance competitive with SOTA DM-based and supervised approaches, despite not requiring large amounts of clean training data.

Related papers

• Enhancing pretraining efficiency for medical image segmentation via transferability metrics [0.0]
  In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge. We introduce a novel transferability metric, based on contrastive learning, that measures how robustly a pretrained model is able to represent the target data.
  arXiv  Detail & Related papers  (2024-10-24T12:11:52Z)
• Improved Distribution Matching Distillation for Fast Image Synthesis [54.72356560597428]
  We introduce DMD2, a set of techniques that lift this limitation and improve DMD training. First, we eliminate the regression loss and the need for expensive dataset construction. Second, we integrate a GAN loss into the distillation procedure, discriminating between generated samples and real images.
  arXiv  Detail & Related papers  (2024-05-23T17:59:49Z)
• Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data [54.09959775518994]
  We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data.<n>We train diffusion models for MRI with access only to subsampled multi-coil measurements at acceleration factors R= 2,4,6,8.<n>For MRI reconstruction in high acceleration regimes, we observe that A-DPS models trained on subsampled data are better suited to solving inverse problems than models trained on fully sampled data.
  arXiv  Detail & Related papers  (2024-03-13T17:28:20Z)
• Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery [78.43828998065071]
  Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities.
  arXiv  Detail & Related papers  (2024-03-08T16:18:04Z)
• Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging [8.34398674359296]
  Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations for all training samples. To address this challenge, deep learning models can be pre-trained on large image datasets without annotations using methods from the field of self-supervised learning.
  arXiv  Detail & Related papers  (2023-08-12T11:31:01Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• Multiscale Structure Guided Diffusion for Image Deblurring [24.09642909404091]
  Diffusion Probabilistic Models (DPMs) have been employed for image deblurring. We introduce a simple yet effective multiscale structure guidance as an implicit bias. We demonstrate more robust deblurring results with fewer artifacts on unseen data.
  arXiv  Detail & Related papers  (2022-12-04T10:40:35Z)
• Stable Optimization for Large Vision Model Based Deep Image Prior in Cone-Beam CT Reconstruction [6.558735319783205]
  Large Vision Model (LVM) has recently demonstrated great potential for medical imaging tasks. Deep Image Prior (DIP) effectively guides an untrained neural network to generate high-quality CBCT images without any training data. We propose a stable optimization method for the forward-model-free DIP model for sparse-view CBCT.
  arXiv  Detail & Related papers  (2022-03-23T15:16:29Z)
• Denoising Diffusion Restoration Models [110.1244240726802]
  Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
  arXiv  Detail & Related papers  (2022-01-27T20:19:07Z)
• Data augmentation for deep learning based accelerated MRI reconstruction with limited data [46.44703053411933]
  Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. To achieve state-of-the-art performance, training on large and diverse sets of images is considered critical. We propose a pipeline for data augmentation for accelerated MRI reconstruction and study its effectiveness at reducing the required training data.
  arXiv  Detail & Related papers  (2021-06-28T19:08:46Z)
• Zero-Shot Self-Supervised Learning for MRI Reconstruction [4.542616945567623]
  We propose a zero-shot self-supervised learning approach to perform subject-specific accelerated DL MRI reconstruction. The proposed approach partitions the available measurements from a single scan into three disjoint sets. In the presence of models pre-trained on a database with different image characteristics, we show that the proposed approach can be combined with transfer learning for faster convergence time and reduced computational complexity.
  arXiv  Detail & Related papers  (2021-02-15T18:34:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.