Self-Organized Residual Blocks For Image Super-Resolution

Keleş, Onur; Tekalp, A. Murat; Malik, Junaid; Kıranyaz, Serkan

doi:10.1109/icip42928.2021.9506260

Cited by 9 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A self-organized residual (SOR) block can be obtained by replacing all regular convolutional layers in a residual block with self-organized layers (SOL) formed by generative neurons without the activation function σ(). (Keleş et al, 2021a), where SOL stands for a layer formed by generative neurons without an activation function.…”

Section: Self-organized Residual Blocksmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Image/Video Restoration and Super-resolution

Tekalp¹

2022

View full text Add to dashboard Cite

Recent advances in neural signal processing led to significant improvements in the performance of learned image/video restoration and super-resolution (SR). An important benefit of data-driven deep learning approach to image processing is that neural models can be optimized for any differentiable loss function, including perceptual loss functions, leading to perceptual image/video restoration and SR, which cannot be easily handled by traditional model-based methods.We start with a brief problem statement and a short discussion on traditional vs. data-driven solutions. We next review recent advances in neural architectures, such as residual blocks, dense connections, residual-in-residual dense blocks, residual blocks with generative neurons, self-attention and visual transformers. We then discuss loss functions and evaluation (assessment) criteria for image/video restoration and SR, including fidelity (distortion) and perceptual criteria, and the relation between them, where we briefly review the perception vs. distortion trade-off.We can consider learned image/video restoration and SR as learning either a nonlinear regressive mapping from degraded to ideal images based on the universal approximation theorem, or a generative model that captures the probability distribution of ideal images. We first review regressive

show abstract

Section: Self-organized Residual Blocksmentioning

confidence: 99%

“…Figure 2.8: Illustration of SOR block(Keleş et al, 2021a), where SOL stands for a layer formed by generative neurons without an activation function.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Image/Video Restoration and Super-resolution

Tekalp¹

2022

View full text Add to dashboard Cite

show abstract

“…In this study, to address the aforementioned limitations, we propose Operational Segmentation Network (OSegNet) that performs COVID-19 pneumonia segmentation for the diagnosis using CXR images. Contrary to convolutional layers used in many deep networks, operational layers with generative neurons of Self-Organized Operational Neural Networks (Self-ONNs) [18][19][20][21][22] are used in the decoder block. Self-ONNs are heterogeneous network models with generative neurons that can create any non-linear transformation in each kernel element.…”

Section: Introductionmentioning

confidence: 99%

Osegnet: Operational Segmentation Network for Covid-19 Detection Using Chest X-Ray Images

Degerli

Kıranyaz

Chowdhury

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Coronavirus disease 2019 (COVID-19) has been diagnosed automatically using Machine Learning algorithms over chest X-ray (CXR) images. However, most of the earlier studies used Deep Learning models over scarce datasets bearing the risk of overfitting. Additionally, previous studies have revealed the fact that deep networks are not reliable for classification since their decisions may originate from irrelevant areas on the CXRs. Therefore, in this study, we propose Operational Segmentation Network (OSegNet) that performs detection by segmenting COVID-19 pneumonia for a reliable diagnosis. To address the data scarcity encountered in training and especially in evaluation, this study extends the largest COVID-19 CXR dataset: QaTa-COV19 with 121, 378 CXRs including 9258 COVID-19 samples with their corresponding ground-truth segmentation masks that are publicly shared with the research community. Consequently, OSegNet has achieved a detection performance with the highest accuracy of 99.65% among the state-of-the-art deep models with 98.09% precision.

show abstract

“…In this neuron model, the non-linear transformation function is approximated via Taylor-series expansion and the model's weights (trainable parameters) are the approximated function coefficients. It is shown that in several classification and denoising applications, the Self-Organized Operational Neural Networks (Self-ONNs) with the 2D-operational layers [13][14][15][16] encapsulating generative neurons have achieved improved performance levels compared to the Convolutional Neural Networks (CNNs) with Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection

Ahishali¹,

Kıranyaz²,

Ahmad³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The band selection in the hyperspectral image (HSI) data processing is an important task considering its effect on the computational complexity and accuracy. In this work, we propose a novel framework for the band selection problem: Self-Representation Learning (SRL) with Sparse 1D-Operational Autoencoder (SOA). The proposed SLR-SOA approach introduces a novel autoencoder model, SOA, that is designed to learn a representation domain where the data are sparsely represented. Moreover, the network composes of 1D-operational layers with the non-linear neuron model. Hence, the learning capability of neurons (filters) is greatly improved with shallow architectures. Using compact architectures is especially crucial in autoencoders as they tend to overfit easily because of their identity mapping objective. Overall, we show that the proposed SRL-SOA band selection approach outperforms the competing methods over two HSI data including Indian Pines and Salinas-A considering the achieved land cover classification accuracies. The software implementation of the SRL-SOA approach is shared publicly 1 .

show abstract

Self-Organized Residual Blocks For Image Super-Resolution

Cited by 9 publications

References 14 publications

Deep Learning for Image/Video Restoration and Super-resolution

Deep Learning for Image/Video Restoration and Super-resolution

Osegnet: Operational Segmentation Network for Covid-19 Detection Using Chest X-Ray Images

SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection

Contact Info

Product

Resources

About