Equivariant Splitting: Self-supervised learning from incomplete data
Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equivariance in the context of reconstruction networks, and show that the combination of self-supervised splitting losses and equivariant reconstruction networks results in unbiased estimates of the supervised loss. Through a series of experiments on image inpainting, accelerated magnetic resonance imaging, sparse-view computed tomography, and compressive sensing, we demonstrate that the proposed loss achieves state-of-the-art performance in settings with highly rank-deficient forward models. The code is available at https://github.com/vsechaud/Equivariant-Splitting
Code (0)
등록된 구현이 없습니다.
Tasks
Self-Supervised LearningCompressive SensingImage InpaintingSimilar Papers 제목 키워드 기반
Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation has attracted much research interest in recent years considering its advantage of low labeling cost. Most of the advanced algorithms follow the design principle that expands and co…
SegmentationSemantic SegmentationWeakly-supervised LearningWeakly supervised Semantic Segmentation+1Design Choices in Splitting-Based Self-Supervised Sparse-View CT Reconstruction
Self-supervised data splitting has emerged as a promising paradigm for sparse-view CT reconstruction, enabling training from incomplete measurements without fully sampled ground truth. However, the influence of key desig…
Fast Equivariant Imaging: Accelerating Unsupervised Learning and Model Adaptation via Inexact Splitting
In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging networks without ground-truth data. FEI reformulates the EI objective through…
Test-time AdaptationImage InpaintingScale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and Deblurring
Self-supervised methods have recently proved to be nearly as effective as supervised ones in various imaging inverse problems, paving the way for learning-based approaches in scientific and medical imaging applications w…
DeblurringImage Super-ResolutionSelf-Supervised LearningSuper-ResolutionSelf-Supervised Learning for Group Equivariant Neural Networks
This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with th…
Self-Supervised Learning