DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10337-10348
DOI: 10.1109/tpami.2024.3450575 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Vishwanath Saragadam und 3 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: NSF, ONR, Air Force Office of Scientific Research.
Abstract (Originalsprache)
DeepTensor is a computationally efficient framework for low-rank decomposition of matrices and tensors using deep generative networks. We decompose a tensor as the product of low-rank tensor factors (e.g., a matrix as the outer product of two vectors), where each low-rank tensor is generated by a deep network (DN) that is trained in a self-supervised manner to minimize the mean-square approximation error. Our key observation is that the implicit regularization inherent in DNs enables them to capture nonlinear signal structures (e.g., manifolds) that are out of the reach of classical linear methods like the singular value decomposition (SVD) and principal components analysis (PCA). Furthermore, in contrast to the SVD and PCA, whose performance deteriorates when the tensor's entries deviate from additive white Gaussian noise, we demonstrate that the performance of DeepTensor is robust to a wide range of distributions. We validate that DeepTensor is a robust and computationally efficient drop-in replacement for the SVD, PCA, nonnegative matrix factorization (NMF), and similar decompositions by exploring a range of real-world applications, including hyperspectral image denoising, 3D MRI tomography, and image classification. In particular, DeepTensor offers a 6 dB signal-to-noise ratio improvement over standard denoising methods for signal corrupted by Poisson noise and learns to decompose 3D tensors 60 times faster than a single DN equipped with 3D convolutions.
Förderung
- NSF
- ONR
- Air Force Office of Scientific Research
- Vannevar Bush Faculty Fellowship
Zitieren
APA
Saragadam, V., Balestriero, R., Veeraraghavan, A., & Baraniuk, R. G. (2024). DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10337-10348. https://doi.org/10.1109/tpami.2024.3450575
Vancouver
Saragadam V, Balestriero R, Veeraraghavan A, Baraniuk RG. DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10337-10348. doi:10.1109/tpami.2024.3450575
BibTeX
@article{Saragadam2024,
author = {Saragadam, Vishwanath and Balestriero, Randall and Veeraraghavan, Ashok and Baraniuk, Richard G},
title = {DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {10337--10348},
doi = {10.1109/tpami.2024.3450575}
}
EUVIMED