SDAT: Sub-Dataset Alternation Training for Improved Image Demosaicing

Image demosaicing is an important step in the image processing pipeline for digital cameras. In data centric approaches, such as deep learning, the distribution of the dataset used for training can impose a bias on the networks' outcome. For example, in natural images most patches are smooth, a...

Full description

Saved in:
Bibliographic Details
Published inIEEE open journal of signal processing Vol. 5; pp. 611 - 620
Main Authors Becker, Yuval, Nossek, Raz Z., Peleg, Tomer
Format Journal Article
LanguageEnglish
Published New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Algorithms
Benchmark testing
Bias
Convergence
Datasets
Deep learning
Demosaicing
Digital cameras
Digital imaging
Image color analysis
Image processing
Image reconstruction
Image restoration
inductive bias
Machine learning
Task analysis
Training
Online AccessGet full text

Cover

More Information
Summary:Image demosaicing is an important step in the image processing pipeline for digital cameras. In data centric approaches, such as deep learning, the distribution of the dataset used for training can impose a bias on the networks' outcome. For example, in natural images most patches are smooth, and high-content patches are much rarer. This can lead to a bias in the performance of demosaicing algorithms. Most deep learning approaches address this challenge by utilizing specific losses or designing special network architectures. We propose a novel approach SDAT , Sub-Dataset Alternation Training, that tackles the problem from a training protocol perspective. SDAT is comprised of two essential phases. In the initial phase, we employ a method to create sub-datasets from the entire dataset, each inducing a distinct bias. The subsequent phase involves an alternating training process, which uses the derived sub-datasets in addition to training also on the entire dataset. SDAT can be applied regardless of the chosen architecture as demonstrated by various experiments we conducted for the demosaicing task. The experiments are performed across a range of architecture sizes and types, namely CNNs and transformers. We show improved performance in all cases. We are also able to achieve state-of-the-art results on three highly popular image demosaicing benchmarks.
ISSN:2644-1322
2644-1322
DOI:10.1109/OJSP.2024.3395179