Probing shallower: Perceptual loss trained Phase Extraction Neural Network (PLT-PhENN) for artifact-free reconstruction at low photon budget
Optics Express, ISSN: 1094-4087, Vol: 28, Issue: 2, Page: 2511-2535
2020
- 20Citations
- 26Captures
Metric Options: Counts1 Year3 YearSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Metrics Details
- Citations20
- Citation Indexes20
- CrossRef20
- 17
- Captures26
- Readers26
- 26
Article Description
Deep neural networks (DNNs) are efficient solvers for ill-posed problems and have been shown to outperform classical optimization techniques in several computational imaging problems. In supervised mode, DNNs are trained by minimizing a measure of the difference between their actual output and their desired output; the choice of measure, referred to as “loss function,” severely impacts performance and generalization ability. In a recent paper [A. Goy et al., Phys. Rev. Lett. 121(24), 243902 (2018)], we showed that DNNs trained with the negative Pearson correlation coefficient (NPCC) as the loss function are particularly fit for photon-starved phase-retrieval problems, though the reconstructions are manifestly deficient at high spatial frequencies. In this paper, we show that reconstructions by DNNs trained with default feature loss (defined at VGG layer ReLU-22) contain more fine details; however, grid-like artifacts appear and are enhanced as photon counts become very low. Two additional key findings related to these artifacts are presented here. First, the frequency signature of the artifacts depends on the VGG’s inner layer that perceptual loss is defined upon, halving with each MaxPooling2D layer deeper in the VGG. Second, VGG ReLU-12 outperforms all other layers as the defining layer for the perceptual loss.
Bibliographic Details
http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85078512927&origin=inward; http://dx.doi.org/10.1364/oe.381301; http://www.ncbi.nlm.nih.gov/pubmed/32121939; https://opg.optica.org/abstract.cfm?URI=oe-28-2-2511; https://dx.doi.org/10.1364/oe.381301; https://opg.optica.org/oe/fulltext.cfm?uri=oe-28-2-2511&id=426045
Optica Publishing Group
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know