Search

Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial examples (AEs). Denoising based on the input pre-processing is one of the defenses against adversarial attacks. However, it is hard to remove multiple adversarial perturbations, especially in the presence of evolving attacks. To address this challenge, we attempt to extract the commonality of adversarial perturbations. Due to the imperceptibility of adversarial perturbations in the input space, we conduct the extraction in the deep feature space where the perturbations become more apparent. Through the obtained common characteristics, we craft common adversarial examples (CAEs) to train the denoiser. Furthermore, to prevent image distortion while removing as much of the adversarial perturbation as possible, we propose a hybrid loss function that guides the training process at both the pixel level and the deep feature space. Our experiments show that our defense method can eliminate multiple adversarial perturbations, significantly enhancing adversarial robustness compared to previous state-of-the-art methods. Moreover, it can be plug-and-play for various classification models, which demonstrates the generalizability of our defense method. [ABSTRACT FROM AUTHOR]

Approximate message passing-based compressive sensing reconstruction has received increasing attention, the performance of which depends heavily on the ability of the denoising operator. However, most methods only employ an off-the-shelf denoising model as the denoising operator of the iteration solver, which imposes an unfavorable limit on reconstruction performance of compressive sensing. To solve the aforementioned issue, we propose a novel versatile denoising-based approximate message passing model, abbreviated as VD-AMP, for compressive sensing (CS) recovery. To be specific, we meticulously design a double encoder-decoder denoising network (DEDNet), which manifests the impressive performance in Gaussian denoising. Moreover, a fine-grained noise level division (FNLD) solution is proposed to release the potential of the well-designed DEDNet so as to improve the reconstruction performance. However, strengthening the denoiser alone fails to remove the distortion artifact of reconstruction images at low sampling rates. To alleviate the defect, we propose an anti-aliasing sampling (AS), which firstly maps the input image to a smoothing sub-space using the proposed DEDNet before vanilla sampling, reducing aliasing between high-frequency and low-frequency information on measurement. Extensive experiments on benchmark datasets demonstrate that the proposed VD-AMP significantly outperforms state-of-the-art CS reconstruction models by a large margin, e.g., up to 2 dB gains on PSNR. [ABSTRACT FROM AUTHOR]

Speckle is a multiplicative granular noise that naturally occurs in the images captured by coherent imaging sensors such as synthetic aperture radar (SAR). It visually degrades the underlying image information and has an impact on subsequent image analysis. This problem is addressed here by developing a sparse representation model and applying an alternating minimization scheme for SAR image despeckling. The proposed method directly deals with the multiplicative noise and the data model is formed by utilizing the speckle statistics. The similar patches are clustered together to adaptively learn the dictionary, and the sparse coefficients are updated using plug-and-play based fast iterative shrinkage threshold algorithm (PnP-FISTA). Finally, the clean image is estimated using Newton’s method. Experiments on simulated and practical SAR images signify that the proposed method performs better compared to the state-of-the-art methods in terms of performance metrics and visual assessment. [ABSTRACT FROM AUTHOR]

In this article, a neural network (NN) approach is introduced to estimate the nonnoisy speed and torque from noisy measured currents and voltages in induction motors with variable speed drives. The proposed estimation method is comprised of a neural speed–torque estimator and a neural signal denoiser. A new training strategy is introduced that combines large amount of simulated data and a small amount of real-world data. The proposed denoiser does not require nonnoisy ground-truth data for training, and instead uses classification labels that are easily generated from real-world data. This approach improves upon existing noise removal techniques by learning to denoise as well as classify noisy signals into static and dynamic parts. The proposed NN-based denoiser generates clean estimates of currents and voltages that are then used as inputs to the NN estimator of speed and torque. Extensive experiments show that the proposed joint denoising-estimation strategy performs very well on real data benchmarks. The proposed denoising method is shown to outperform several widely used denoising methods and a proper ablation study of the proposed method is conducted. [ABSTRACT FROM AUTHOR]

Simple Summary: We investigated the contouring data of organs at risk from 40 patients with breast cancer who underwent radiotherapy. The performance of denoising-based auto-segmentation was compared with manual segmentation and conventional deep-learning-based auto-segmentation without denoising. Denoising-based auto-segmentation achieved superior segmentation accuracy on the liver compared with AccuContourTM-based auto-segmentation. This denoising-based auto-segmentation method could provide more precise contour delineation of the liver and reduce the clinical workload. Objective: This study aimed to investigate the segmentation accuracy of organs at risk (OARs) when denoised computed tomography (CT) images are used as input data for a deep-learning-based auto-segmentation framework. Methods: We used non-contrast enhanced planning CT scans from 40 patients with breast cancer. The heart, lungs, esophagus, spinal cord, and liver were manually delineated by two experienced radiation oncologists in a double-blind manner. The denoised CT images were used as input data for the AccuContourTM segmentation software to increase the signal difference between structures of interest and unwanted noise in non-contrast CT. The accuracy of the segmentation was assessed using the Dice similarity coefficient (DSC), and the results were compared with those of conventional deep-learning-based auto-segmentation without denoising. Results: The average DSC outcomes were higher than 0.80 for all OARs except for the esophagus. AccuContourTM-based and denoising-based auto-segmentation demonstrated comparable performance for the lungs and spinal cord but showed limited performance for the esophagus. Denoising-based auto-segmentation for the liver was minimal but had statistically significantly better DSC than AccuContourTM-based auto-segmentation (p < 0.05). Conclusions: Denoising-based auto-segmentation demonstrated satisfactory performance in automatic liver segmentation from non-contrast enhanced CT scans. Further external validation studies with larger cohorts are needed to verify the usefulness of denoising-based auto-segmentation. [ABSTRACT FROM AUTHOR]

Neural networks are very vulnerable to adversarial examples, which threaten their application in security systems, such as face recognition, and autopilot. In response to this problem, we propose a new defensive strategy. In our strategy, we propose a new deep denoising neural network, which is called UDDN, to remove the noise on adversarial samples. The standard denoiser suffers from the amplification effect, in which the small residual adversarial noise gradually increases and leads to misclassification. The proposed denoiser overcomes this problem by using a special loss function, which is defined as the difference between the model outputs activated by the original image and denoised image. At the same time, we propose a new model training algorithm based on knowledge transfer, which can resist slight image disturbance and make the model generalize better around the training samples. Our proposed defensive strategy is robust against both white-box or black-box attacks. Meanwhile, the strategy is applicable to any deep neural network-based model. In the experiment, we apply the defensive strategy to a face recognition model. The experimental results show that our algorithm can effectively resist adversarial attacks and improve the accuracy of the model. [ABSTRACT FROM AUTHOR]

Neural networks are very vulnerable to adversarial examples, which threaten their application in security systems, such as face recognition, and autopilot. In response to this problem, we propose a new defensive strategy. In our strategy, we propose a new deep denoising neural network, which is called UDDN, to remove the noise on adversarial samples. The standard denoiser suffers from the amplification effect, in which the small residual adversarial noise gradually increases and leads to misclassification. The proposed denoiser overcomes this problem by using a special loss function, which is defined as the difference between the model outputs activated by the original image and denoised image. At the same time, we propose a new model training algorithm based on knowledge transfer, which can resist slight image disturbance and make the model generalize better around the training samples. Our proposed defensive strategy is robust against both white-box or black-box attacks. Meanwhile, the strategy is applicable to any deep neural network-based model. In the experiment, we apply the defensive strategy to a face recognition model. The experimental results show that our algorithm can effectively resist adversarial attacks and improve the accuracy of the model.

A denoising algorithm seeks to remove noise, errors, or perturbations from a signal. Extensive research has been devoted to this arena over the last several decades, and as a result, todays denoisers can effectively remove large amounts of additive white Gaussian noise. A compressed sensing (CS) reconstruction algorithm seeks to recover a structured signal acquired using a small number of randomized measurements. Typical CS reconstruction algorithms can be cast as iteratively estimating a signal from a perturbed observation. This paper answers a natural question: How can one effectively employ a generic denoiser in a CS reconstruction algorithm? In response, we develop an extension of the approximate message passing (AMP) framework, called denoising-based AMP (D-AMP), that can integrate a wide class of denoisers within its iterations. We demonstrate that, when used with a high-performance denoiser for natural images, D-AMP offers the state-of-the-art CS recovery performance while operating tens of times faster than competing methods. We explain the exceptional performance of D-AMP by analyzing some of its theoretical features. A key element in D-AMP is the use of an appropriate Onsager correction term in its iterations, which coerces the signal perturbation at each iteration to be very close to the white Gaussian noise that denoisers are typically designed to remove. [ABSTRACT FROM PUBLISHER]

Speckle noise removal is a well-established problem in synthetic aperture radar (SAR) image processing. Among different methods focused on the reconstruction of SAR images, variational models have achieved state-of-the-art performance. In this paper, a Rayleigh based speckle reduction algorithm is developed using the variational framework. The forward model is combined with recently proposed regularization by denoising (RED) prior. However, RED has been proposed in literature for the additive noise model. Multiplicative noise in SAR images prevents the direct application of RED to variational models. Hence, logarithm transformation is applied to change the multiplicative noise model to additive model, and the forward model from Rayleigh to Fisher–Tippett distribution. The resulting optimization problem is solved using the alternating direction method of multipliers. Further, the proof of the convergence analysis is carried out for the above framework. Simulations convey that the proposed method has better despeckling performance compared to that of state-of-the-art methods. • The convex RED-based variational model is proposed for speckle reduction and edge preservation in SAR images. • The optimization model is numerically solved by constructing the augmented Lagrangian and employing ADMM. • The residual convergence is derived both mathematically and empirically for each of the ADMM sub-problems. • The despeckling accuracy is determined by comparing the proposed work with seven state-of the-art methods for both simulated and practical SAR images. [ABSTRACT FROM AUTHOR]

Dynamic positron emission tomography (PET) imaging can provide information about metabolic changes over time, used for kinetic analysis and auxiliary diagnosis. Existing deep learning-based reconstruction methods have too many trainable parameters and poor generalization, and require mass data to train the neural network. However, obtaining large amounts of medical data is expensive and time-consuming. To reduce the need for data and improve the generalization of network, we combined the filtered back-projection (FBP) algorithm with neural network, and proposed FBP-Net which could directly reconstruct PET images from sinograms instead of post-processing the rough reconstruction images obtained by traditional methods. The FBP-Net contained two parts: the FBP part and the denoiser part. The FBP part adaptively learned the frequency filter to realize the transformation from the detector domain to the image domain, and normalized the coarse reconstruction images obtained. The denoiser part merged the information of all time frames to improve the quality of dynamic PET reconstruction images, especially the early time frames. The proposed FBP-Net was performed on simulation and real dataset, and the results were compared with the state-of-art U-net and DeepPET. The results showed that FBP-Net did not tend to overfit the training set and had a stronger generalization., (Creative Commons Attribution license.)