neural Architecture Search (NAS) aims to automate the design process of Deep neuralnetworks (DNN) without requiring profound domain knowledge. The Deep Genetic Algorithm (DeepGA) was proposed to find the architecture...
详细信息
Modern deep neuralnetworks have made numerous breakthroughs in real-world applications, yet they remain vulnerable to some imperceptible adversarial perturbations. These tailored perturbations can severely disrupt th...
详细信息
Modern deep neuralnetworks have made numerous breakthroughs in real-world applications, yet they remain vulnerable to some imperceptible adversarial perturbations. These tailored perturbations can severely disrupt the inference of current deep learning-based methods and may induce potential security hazards to artificial intelligence applications. So far, adversarial training methods have achieved excellent robustness against various adversarial attacks by involving adversarial examples during the training stage. However, existing methods primarily rely on optimizing injective adversarial examples correspondingly generated from natural examples, ignoring potential adversaries in the adversarial domain. This optimization bias can induce the overfitting of the suboptimal decision boundary, which heavily jeopardizes adversarial robustness. To address this issue, we propose Adversarial Probabilistic Training (APT) to bridge the distribution gap between the natural and adversarial examples via modeling the latent adversarial distribution. Instead of tedious and costly adversary sampling to form the probabilistic domain, we estimate the adversarial distribution parameters in the feature level for efficiency. Moreover, we decouple the distribution alignment based on the adversarial probability model and the original adversarial example. We then devise a novel reweighting mechanism for the distribution alignment by considering the adversarial strength and the domain uncertainty. Extensive experiments demonstrate the superiority of our adversarial probabilistic training method against various types of adversarial attacks in different datasets and scenarios.
Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting...
Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in imageprocessing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificialneuralnetworks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neuralnetworks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neuralnetworks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learnin
The proceedings contain 9 papers. The special focus in this conference is on Design and Architecture for Signal and imageprocessing. The topics include: sEMG-Based Gesture Recognition with Spiking neural Network...
ISBN:
(纸本)9783031628733
The proceedings contain 9 papers. The special focus in this conference is on Design and Architecture for Signal and imageprocessing. The topics include: sEMG-Based Gesture Recognition with Spiking neuralnetworks on Low-Power FPGA;A Highly Configurable Platform for Advanced PPG Analysis;preface;Standalone Nested Loop Acceleration on CGRAs for Signal processingapplications;optimising Graph Representation for Hardware Implementation of Graph Convolutional networks for Event-Based Vision;Improving the Energy Efficiency of CNN Inference on FPGA Using Partial Reconfiguration;scratchy: A Class of Adaptable Architectures with Software-Managed Communication for Edge Streaming applications.
Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical image Registration, Multi...
详细信息
Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical image Registration, Multi-lingual translation, Local language processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.
Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many m...
详细信息
ISBN:
(纸本)9783031776090;9783031776106
Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many medical applications, for example magnetic resonance imaging (MRI), rely on complex-valued signal processing techniques for data acquisition and analysis. However, the appropriate application of DP to complex-valued data is still underexplored. To address this issue, from the theoretical side, we introduce the complex-valued Gaussian mechanism, whose behaviour we characterise in terms of f-DP, (epsilon, delta)-DP and Renyi-DP. Moreover, we generalise the fundamental algorithm DP stochastic gradient descent to complex-valued neuralnetworks and present novel complex-valued neural network primitives compatible with DP. Experimentally, we showcase a proof-of-concept by training federated complex-valued neuralnetworks with DP on a real-world task (MRI pulse sequence classification in k-space), yielding excellent utility and privacy. Our results highlight the relevance of combining federated learning with robust privacy-preserving techniques in the MRI context.
image super-resolution (SR) is currently a very active research topic with applications spanning from computer vision to videos and graphic industries. The top performers in SR field usually employ deep or wide convol...
详细信息
Segmentation of cone-beam computed tomography (CBCT) images plays an important role in clinical treatment as well as teaching. Traditional manual segmentation of dental CBCT images requires tools such as mimics and is...
详细信息
Segmentation of cone-beam computed tomography (CBCT) images plays an important role in clinical treatment as well as teaching. Traditional manual segmentation of dental CBCT images requires tools such as mimics and is time-consuming. With the development of deep learning, the U-shaped network, represented by UNet, has shown good results. Due to the significant improvement brought by various applications of Transformers to image tasks, more and more models try to combine attention mechanism with traditional convolutional neuralnetworks. To further improve the performance of dental CBCT segmentation, this paper proposes an improved FlowgateUNet segmentation network, which uses the FlowFormer instead of Transformer in the encoder to achieve attention computation with nearly linear complexity. It also uses the feature map containing global information as the gating signal in the skip connections to further extract relevant features and fuses the results from multiple decoders as the output. Compared to TransUnet, the proposed FlowgateUnet model improved the Dice similarity coefficient (DSC) by 1% on the dental CBCT image dataset, by 0.7% on the dental microCT dataset, and by 2% on the Synapse dataset.
Deep neuralnetworks (DNNs) are popular in imageprocessing but are vulnerable to adversarial attacks, which makes their deployment in security-sensitive systems risky. Adversarial attacks reduce the performance of DN...
详细信息
Deep neuralnetworks (DNNs) are popular in imageprocessing but are vulnerable to adversarial attacks, which makes their deployment in security-sensitive systems risky. Adversarial attacks reduce the performance of DNNs by generating adversarial examples (AEs). In this paper, we propose a novel method called Trans-IFFT-FGSM (Transformer Inverse Finite Fourier Transform Fast Gradient Sign Method) to generate adversarial examples. Unlike others, we apply multiple steps, adding imperceptible perturbation and saving input noise information to create strong AEs, while emphasizing simplicity, efficiency, robustness through iterations, and analytical precision on specific models. We evaluate and compare perturbation generated by Trans-IFFT-FGSM and other attack methods, including FGSM, PGD, DeepFool, and C &W on imageNet and MNIST, and evaluation results suggest that Trans-IFFT-FGSM achieves a high attack success rate (ASR) and attack accuracy. In addition, we compare Trans-IFFT-FGSM and other attack methods under the existence of a defense method, which denoises the AEs generated by these methods, and the evaluation results also suggest Trans-IFFT-FGSM outperforms other methods.
Imaging transmission plays an important role in endoscopic clinical diagnosis involved in modern medical treatment. However, image distortion due to various reasons has been a major obstacle to state-of-art endoscopic...
详细信息
Imaging transmission plays an important role in endoscopic clinical diagnosis involved in modern medical treatment. However, image distortion due to various reasons has been a major obstacle to state-of-art endoscopic development. Here, as a preliminary study we demonstrate ultra-efficient recovery of exemplary 2D color images transmitted by a disturbed graded-index (GRIN) imaging system through the deep neuralnetworks (DNNs). Indeed, the GRIN imaging system can preserve analog images through the GRIN waveguides with high quality, while the DNNs serve as an efficient tool for imaging distortion correction. Combining GRIN imaging systems and DNNs can greatly reduce the training process and achieve ideal imaging transmission. We consider imaging distortion under different realistic conditions and use both pix2pix and U-net type DNNs to restore the images, indicating the suitable network in each condition. This method can automatically cleanse the distorted images with superior robustness and accuracy, which can potentially be used in minimally invasive medical applications. & COPY;2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
暂无评论