Wavelet neuralnetworks are a unique combination of wavelet analysis and neural network architectures, thus providing the benefits of advanced signal processing. Unlike traditional methods, WNNs offer a multi-resoluti...
详细信息
Skin is a vital organ in our body and it even serves as a shield against harmful rays. If skin gets some of the problems, then it would affect the whole body. Major reason for the skin cancer is due to ultraviolet ray...
详细信息
Deep neuralnetworks (DNNs) are adopted in numerous application areas of signal and information processing with Convolutional neuralnetworks (CNNs) being a particularly popular class of DNNs. Many machinelearning (M...
详细信息
ISBN:
(数字)9781510661714
ISBN:
(纸本)9781510661707;9781510661714
Deep neuralnetworks (DNNs) are adopted in numerous application areas of signal and information processing with Convolutional neuralnetworks (CNNs) being a particularly popular class of DNNs. Many machinelearning (ML) frameworks have evolved for design and training of CNN models, and similarly, a wide variety of target platforms, ranging from mobile and resource-constrained platforms to desktop and more powerful platforms, are used to deploy CNN-equipped applications. To help designers navigate the complex design spaces involved in deploying CNN models derived from ML frameworks on alternative processing platforms, retargetable methods for implementing CNN models are of increasing interest. In this paper, we present a novel software tool, called the Lightweight-dataflow-based CNN Inference Package (LCIP), for retargetable, optimized CNN inference on different hardware platforms (e.g., x86 and ARM CPUs, and GPUs). In LCIP, source code for CNN operators (convolution, pooling, etc.) derived from ML frameworks is wrapped within dataflow actors. The resulting coarse grain dataflow models are then optimized using the retargetable LCIP runtime engine, which employs higherlevel dataflow analysis and orchestration that is complementary to the intra-operator performance optimizations provided by the ML framework and the back-end development tools of the target platform. Additionally, LCIP enables heterogeneous and distributed edge inference of CNNs by offloading part of the CNN to additional devices, such as onboard GPU or network devices. Our experimental results show that LCIP provides significant improvements in inference throughput on commonly-used CNN architectures, and the improvement is consistent across desktop and resource-constrained platforms.
image classification is a domain of machinelearning, involving the techniques used to distinguish between images. Various parameters are taken into account such as pixel density, curves and edges, etc. There are vari...
详细信息
This paper presents a new approach for robotically colourizing grayscale photographs with the use of Generative antagonistic networks (GANs). First, an encoderdecoder neural community is used to generate a low-resolut...
详细信息
image reconstruction and super resolution has various applications. Several deep learning techniques are being employed to constantly improve this space. The aim of this experiment is to showcase a unique deep learnin...
详细信息
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual exp...
详细信息
ISBN:
(纸本)9781713899921
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations. However, Saliency Maps generated by traditional neuralnetworks are often noisy and provide limited insights. In this paper, we demonstrate that, on the contrary, the Saliency Maps of 1-Lipschitz neuralnetworks, learned with the dual loss of an optimal transportation problem, exhibit desirable XAI properties: They are highly concentrated on the essential parts of the image with low noise, significantly outperforming state-of-the-art explanation approaches across various models and metrics. We also prove that these maps align unprecedentedly well with human explanations on imageNet. To explain the particularly beneficial properties of the Saliency Map for such models, we prove this gradient encodes both the direction of the transportation plan and the direction towards the nearest adversarial attack. Following the gradient down to the decision boundary is no longer considered an adversarial attack, but rather a counterfactual explanation that explicitly transports the input from one class to another. Thus, learning with such a loss jointly optimizes the classification objective and the alignment of the gradient, i.e. the Saliency Map, to the transportation plan direction. These networks were previously known to be certifiably robust by design, and we demonstrate that they scale well for large problems and models, and are tailored for explainability using a fast and straightforward method.
Cloud-based applications are ubiquitously employed across diverse fields within the ever-evolving landscape of technology, serving as integral roots for innovation and efficiency. A meticulous evaluation of the skin c...
详细信息
Video classification models have become one of the most widely used topics in the computer vision field, encompassing many tasks such as medical, security, industrial, and other applications. Although deep learning mo...
详细信息
ISBN:
(纸本)9798350391893;9798350391886
Video classification models have become one of the most widely used topics in the computer vision field, encompassing many tasks such as medical, security, industrial, and other applications. Although deep learning models have achieved great results in the video domain, such models are built to operate in the domain of RGB frame sequences. In such models, a prior step is required for decoding video data since the vast majority relies on compressed formats. Nevertheless, large amounts of computational resources are required for decoding, especially in real-time. Researchers have already tackled the task of building networks that work in the compressed domain with promising results but with architectures still very close to those used for the RGB domain. We propose an approach that employs neural Architecture Search to explore and find the most effective architectures for the compressed domain. Our approach was tested on UCF101 and HMDB51 datasets, obtaining a computationally less complex architecture than similar methods.
Differentiation between human and non-human objects can increase efficiency of human-robot collaborative applications. This paper proposes to use convolutional neuralnetworks for classifying objects in robotic applic...
详细信息
ISBN:
(纸本)9798350335170
Differentiation between human and non-human objects can increase efficiency of human-robot collaborative applications. This paper proposes to use convolutional neuralnetworks for classifying objects in robotic applications. The body temperature of human beings is used to classify humans and to estimate the distance to the sensor. Using image classification with convolutional neuralnetworks it is possible to detect humans in the surroundings of a robot up to five meters distance with low-cost and low-weight thermal cameras. Using transfer learning technique we trained the GoogLeNet and MobilenetV2. Results show accuracies of 99.48 % and 99.06 % respectively.
暂无评论