Projects per year
In many real-world inverse problems, only incomplete measurement data are available for training which can pose a problem for learning a reconstruction function. Indeed, unsupervised learning using a fixed incomplete measurement process is impossible in general, as there is no information in the nullspace of the measurement operator. This limitation can be overcome by using measurements from multiple operators. While this idea has been successfully applied in various applications, a precise characterization of the conditions for learning is still lacking. In this paper, we fill this gap by presenting necessary and sufficient conditions for learning the underlying signal model needed for reconstruction which indicate the interplay between the number of distinct measurement operators, the number of measurements per operator, the dimension of the model and the dimension of the signals. Furthermore, we propose a novel and conceptually simple unsupervised learning loss which only requires access to incomplete measurement data and achieves a performance on par with supervised learning when the sufficient condition is verified. We validate our theoretical bounds and demonstrate the advantages of the proposed unsupervised loss compared to previous methods via a series of experiments on various imaging inverse problems, such as accelerated magnetic resonance imaging, compressed sensing and image inpainting.
|Publication status||Accepted/In press - 14 Sep 2022|
|Event||The 36th Conference on Neural Information Processing Systems, 2022 - New Orleans, United States|
Duration: 28 Nov 2022 → 9 Dec 2022
Conference number: 36
|Conference||The 36th Conference on Neural Information Processing Systems, 2022|
|Abbreviated title||NeurIPS 2022|
|Period||28/11/22 → 9/12/22|
- I.4.5; I.2.10; G.3
FingerprintDive into the research topics of 'Unsupervised Learning From Incomplete Measurements for Inverse Problems'. Together they form a unique fingerprint.
- 2 Finished
1/10/16 → 30/09/21
1/09/16 → 31/08/22