EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Enhancing convolutional neural network generalizability via low‐rank weight approximation

Chenyin Gao, Shu Yang, Anru R. Zhang

IET Image Processing · 2026-01 · 20 (1)

DOI: 10.1049/ipr2.13205 ↗

At a glance

Journal article in IET Image Processing, published online on 2025-12-29. Written by Chenyin Gao and 2 co-authors. Cited 1 times so far (Crossref); 63 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Science Foundation, National Institutes of Health.

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Noise is ubiquitous during image acquisition. Sufficient denoising is often an important first step for image processing. In recent decades, deep neural networks (DNNs) have been widely used for image denoising. Most DNN‐based image denoising methods require a large‐scale dataset or focus on supervised settings, in which single/pairs of clean images or a set of noisy images are required. This poses a significant burden on the image acquisition process. Moreover, denoisers trained on datasets of limited scale may incur over‐fitting. To mitigate these issues, a new self‐supervised framework for image denoising based on the Tucker low‐rank tensor approximation is introduced. With the proposed design, the authors are able to characterize the denoiser with fewer parameters and train it based on a single image, which considerably improves the model generalizability and reduces the cost of data acquisition. Extensive experiments on both synthetic and real‐world noisy images have been conducted. Empirical results show that the proposed method outperforms existing non‐learning‐based methods (e.g. low‐pass filter, non‐local mean), single‐image unsupervised denoisers (e.g. DIP, NN+BM3D) evaluated on both in‐sample and out‐sample datasets. The proposed method even achieves comparable performances with some supervised methods (e.g. DnCNN).

Funding

  • National Science Foundation
  • National Institutes of Health

Cite

APA

Gao, C., Yang, S., & Zhang, A. R. (2026). Enhancing convolutional neural network generalizability via low‐rank weight approximation. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.13205

Vancouver

Gao C, Yang S, Zhang AR. Enhancing convolutional neural network generalizability via low‐rank weight approximation. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.13205

BibTeX
@article{Gao2026,
  author = {Gao, Chenyin and Yang, Shu and Zhang, Anru R.},
  title = {Enhancing convolutional neural network generalizability via low‐rank weight approximation},
  journal = {IET Image Processing},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/ipr2.13205}
}
Start for free →