Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

We thank the reviewers for carefully reading the manuscript and providing us with valuable feedback. This was omitted from the submitted manuscript due to space. We will clarify L220 to make this more precise. However, we will certainly include citations to both Danielyan and Tseng in the manuscript. L17 to say that the true prior might be unknown for certain signals, such as natural images.

Deep neural networks (DNNs) have shown superior performance comparing to traditional image denoising algorithms. However, DNNs are inevitably vulnerable while facing adversarial attacks. In this paper, we propose an adversarial attack method named denoising-PGD which can successfully attack all the current deep denoising models while keep the noise distribution almost unchanged. We surprisingly find that the current mainstream non-blind denoising models (DnCNN, FFDNet, ECNDNet, BRDNet), blind denoising models (DnCNN-B, Noise2Noise, RDDCNN-B, FAN), plug-and-play (DPIR, CurvPnP) and unfolding denoising models (DeamNet) almost share the same adversarial sample set on both grayscale and color images, respectively. Shared adversarial sample set indicates that all these models are similar in term of local behaviors at the neighborhood of all the test samples. Thus, we further propose an indicator to measure the local similarity of models, called robustness similitude. Non-blind denoising models are found to have high robustness similitude across each other, while hybrid-driven models are also found to have high robustness similitude with pure data-driven non-blind denoising models. According to our robustness assessment, data-driven non-blind denoising models are the most robust. We use adversarial training to complement the vulnerability to adversarial attacks. Moreover, the model-driven image denoising BM3D shows resistance on adversarial attacks.

Noise is ubiquitous during image acquisition. Sufficient denoising is often an important first step for image processing. In recent decades, deep neural networks (DNNs) have been widely used for image denoising. Most DNN-based image denoising methods require a large-scale dataset or focus on supervised settings, in which single/pairs of clean images or a set of noisy images are required. This poses a significant burden on the image acquisition process. Moreover, denoisers trained on datasets of limited scale may incur over-fitting. To mitigate these issues, we introduce a new self-supervised framework for image denoising based on the Tucker low-rank tensor approximation. With the proposed design, we are able to characterize our denoiser with fewer parameters and train it based on a single image, which considerably improves the model generalizability and reduces the cost of data acquisition. Extensive experiments on both synthetic and real-world noisy images have been conducted. Empirical results show that our proposed method outperforms existing non-learning-based methods (e.g., low-pass filter, non-local mean), single-image unsupervised denoisers (e.g., DIP, NN+BM3D) evaluated on both in-sample and out-sample datasets. The proposed method even achieves comparable performances with some supervised methods (e.g., DnCNN).

The biliary tree is a network of tubes that connects the liver to the gallbladder, an organ right beneath it. The bile duct is the major tube in the biliary tree. The dilatation of a bile duct is a key indicator for more major problems in the human body, such as stones and tumors, which are frequently caused by the pancreas or the papilla of vater. The detection of bile duct dilatation can be challenging for beginner or untrained medical personnel in many circumstances. Even professionals are unable to detect bile duct dilatation with the naked eye. This research presents a unique vision-based model for biliary tree initial diagnosis. To segment the biliary tree from the Magnetic Resonance Image, the framework used different image processing approaches (MRI). After the image's region of interest was segmented, numerous calculations were performed on it to extract 10 features, including major and minor axes, bile duct area, biliary tree area, compactness, and some textural features (contrast, mean, variance and correlation). This study used a database of images from King Hussein Medical Center in Amman, Jordan, which included 200 MRI images, 100 normal cases, and 100 patients with dilated bile ducts. After the characteristics are extracted, various classifiers are used to determine the patients' condition in terms of their health (normal or dilated). The findings demonstrate that the extracted features perform well with all classifiers in terms of accuracy and area under the curve. This study is unique in that it uses an automated approach to segment the biliary tree from MRI images, as well as scientifically correlating retrieved features with biliary tree status that has never been done before in the literature.

The recent application of deep learning (DL) to various tasks has seen the performance of classical techniques surpassed by their DL-based counterparts. As a result, DL has equally seen application in the removal of noise from images. In particular, the use of deep feed-forward convolutional neural networks (DnCNNs) has been investigated for denoising. It utilizes advances in DL techniques such as deep architecture, residual learning, and batch normalization to achieve better denoising performance when compared with the other classical state-of-the-art denoising algorithms. However, its deep architecture resulted in a huge set of trainable parameters. Meta-optimization is a training approach of enabling algorithms to learn to train themselves by themselves. Training algorithms using meta-optimizers have been shown to enable algorithms to achieve better performance when compared to the classical gradient descent-based training approach. In this work, we investigate the application of the meta-optimization training approach to the DnCNN denoising algorithm to enhance its denoising capability. Our preliminary experiments on simpler algorithms reveal the prospects of utilizing the meta-optimization training approach towards the enhancement of the DnCNN denoising capability.

Recently, deep learning (DL) methods such as convolutional neural networks (CNNs) have gained prominence in the area of image denoising. This is owing to their proven ability to surpass state-of-the-art classical image denoising algorithms such as BM3D. Deep denoising CNNs (DnCNNs) use many feedforward convolution layers with added regularization methods of batch normalization and residual learning to improve denoising performance significantly. However, this comes at the expense of a huge number of trainable parameters. In this paper, we address this issue by reducing the number of parameters while achieving a comparable level of performance. We derive motivation from the improved performance obtained by training networks using the dense-sparse-dense (DSD) training approach. We extend this training approach to a reduced DnCNN (RDnCNN) network resulting in a faster denoising network with significantly reduced parameters and comparable performance to the DnCNN.

Model protection is vital when deploying Convolutional Neural Networks (CNNs) for commercial services, due to the massive costs of training them. In this work, we propose a selective encryption (SE) algorithm to protect CNN models from unauthorized access, with a unique feature of providing hierarchical services to users. Our algorithm firstly selects important model parameters via the proposed Probabilistic Selection Strategy (PSS). It then encrypts the most important parameters with the designed encryption method called Distribution Preserving Random Mask (DPRM), so as to maximize the performance degradation by encrypting only a very small portion of model parameters. We also design a set of access permissions, using which different amounts of the most important model parameters can be decrypted. Hence, different levels of model performance can be naturally provided for users. Experimental results demonstrate that the proposed scheme could effectively protect the classification model VGG19 by merely encrypting 8% parameters of convolutional layers. We also implement the proposed model protection scheme in the denoising model DnCNN, showcasing the hierarchical denoising services