Show simple item record

AuthorMalik, Junaid
AuthorKiranyaz, Serkan
AuthorYamac, Mehmet
AuthorGabbouj, Moncef
Available date2023-09-24T08:57:19Z
Publication Date2021
Publication NameProceedings - International Conference on Image Processing, ICIP
ResourceScopus
ISSN2381-8549
URIhttp://dx.doi.org/10.1109/ICIP42928.2021.9506240
URIhttp://hdl.handle.net/10576/47891
AbstractDespite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs. Older but computationally more efficient methods such as BM3D remain a popular choice, especially in resource-constrained scenarios. In this study, we aim to find out whether compact neural networks can learn to produce competitive results as compared to BM3D for AWGN image denoising. To this end, we configure networks with only two hidden layers and employ different neuron models and layer widths for comparing the performance with BM3D across different AWGN noise levels. Our results conclusively show that the recently proposed self-organized variant of operational neural networks based on a generative neuron model (Self-ONNs) is not only a better choice as compared to CNNs, but also provide competitive results as compared to BM3D and even significantly surpass it for high noise levels.
Languageen
PublisherIEEE Computer Society
SubjectDiscriminative learning
Image denoising
Operational neural networks
Self-organized operational neural networks
TitleBM3D VS 2-LAYER ONN
TypeConference Paper
Pagination1994-1998
Volume Number2021-September
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record