Discriminative Transfer Learning for General Image Restoration

Xiao, Lei; Heide, Felix; Heidrich, Wolfgang; Schoelkopf, Bernhard; Hirsch, Michael

doi:10.1109/tip.2018.2831925

Cited by 13 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep convolutional neural networks (DCNNs) have achieved great success in various security-crucial tasks [18,19]. For example, Zhang et al [20] introduced an effective and efficient clustering framework that uses deviation-sparse fuzzy c-means w/o neighbor information constraint to build the deep learning model.…”

Section: Dcnns Based Denoisersmentioning

confidence: 99%

Noise2Clean: Cross-Device Side-Channel Traces Denoising with Unsupervised Deep Learning

Wang

Song

et al. 2023

Electronics

View full text Add to dashboard Cite

Deep learning (DL)-based side-channel analysis (SCA) has posed a severe challenge to the security and privacy of embedded devices. During its execution, an attacker exploits physical SCA leakages collected from profiling devices to create a DL model for recovering secret information from victim devices. Despite this success, recent works have demonstrated that certain countermeasures, such as random delay interrupts or clock jitters, would make these attacks more complex and less practical in real-world scenarios. To address this challenge, we present a novel denoising scheme that exploits the U-Net model to pre-process SCA traces for “noises” (i.e., countermeasures) removal. Specifically, we first pre-train the U-Net model on the paired noisy-clean profiling traces to obtain suitable parameters. This model is then fine-tuned on the noisy-only traces collected from the attacking device. The well-trained model will be finally deployed on the attacking device to remove the noises (i.e., countermeasures) from the measured power traces. In particular, a new inductive transfer learning method is also utilized in our scheme to transfer knowledge learned from the source domain (i.e., profiling device) to the target domain (i.e., attacking device) to improve the model’s generalization ability. During our experimental evaluations, we conduct a detailed analysis of various countermeasures separately or combined and show that the proposed denoising model outperforms current state-of-the-art work by a large margin, e.g., a reduction of at least 30% in computation costs and 5× in guessing entropy.

show abstract

Section: Dcnns Based Denoisersmentioning

confidence: 99%

Noise2Clean: Cross-Device Side-Channel Traces Denoising with Unsupervised Deep Learning

Wang

Song

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Image distortion could be seen in the wavelet and DCT transformations domain, so these transformations could be used to evaluate the restored image by extracting the feature in the wavelet or DCT domain [30]. Figure 2 shows an example for image metrics MSE, PSNR, and SSIM for the reference(sharp), distorted, and the restored images [31]. In practical application, the image reference image is not available, so no-reference (NR) IQA is needed to be used.…”

Section: Image Quality Assessmentmentioning

confidence: 99%

Untitled

2021

IJCSES

View full text Add to dashboard Cite

Image restoration is the process of restoring the original image from a degraded one. Images can be affected by various types of noise, such as Gaussian noise, impulse noise, and affected by blurring, which is happened during image recordings like motion blur, Out-of-Focus Blur, and others. Image restoration techniques are used to reverse the effect of noise and blurring. Restoration of distorted images can be done using some information about noise and the blurring nature or without any knowledge about the image degradation process. Researchers have proposed many algorithms in this regard; in this paper, different noise and degradation models and restoration methods will be discussed and review some researches in this field.

show abstract

“…Alternate deblurring and denoising were iteratively applied to fully deblur the image. Note that the proposed method can be extended to different vision tasks by setting matrix H. For instance, besides deblurring or denoising by setting H as the blur kernel or identity matrix, respectively, super-resolution can be achieved for H being a subsampling matrix [47].…”

Section: Ffdnet Denoisingmentioning

confidence: 99%

Blind Deblurring of Saturated Images Based on Optimization and Deep Learning for Dynamic Visual Inspection on the Assembly Line

Wang

Liu

2019

Symmetry

View full text Add to dashboard Cite

Image deblurring can improve visual quality and mitigates motion blur for dynamic visual inspection. We propose a method to deblur saturated images for dynamic visual inspection by applying blur kernel estimation and deconvolution modeling. The blur kernel is estimated in a transform domain, whereas the deconvolution model is decoupled into deblurring and denoising stages via variable splitting. Deblurring predicts the mask specifying saturated pixels, which are then discarded, and denoising is learned via the fast and flexible denoising network (FFDNet) convolutional neural network (CNN) at a wide range of noise levels. Hence, the proposed deconvolution model provides the benefits of both model optimization and deep learning. Experiments demonstrate that the proposed method suitably restores visual quality and outperforms existing approaches with good score improvements.

show abstract

Discriminative Transfer Learning for General Image Restoration

Cited by 13 publications

References 52 publications

Noise2Clean: Cross-Device Side-Channel Traces Denoising with Unsupervised Deep Learning

Noise2Clean: Cross-Device Side-Channel Traces Denoising with Unsupervised Deep Learning

Untitled

Blind Deblurring of Saturated Images Based on Optimization and Deep Learning for Dynamic Visual Inspection on the Assembly Line

Contact Info

Product

Resources

About