We study the problem of distributed stochastic non-convex optimization with intermittent communication. We consider the full participation setting where M machines work in parallel over R communication rounds and the ...
详细信息
ISBN:
(纸本)9781713871088
We study the problem of distributed stochastic non-convex optimization with intermittent communication. We consider the full participation setting where M machines work in parallel over R communication rounds and the partial participation setting where M machines are sampled independently every round from some meta-distribution over machines. We propose and analyze a new algorithm that improves existing methods by requiring fewer and lighter variance reduction operations. We also present lower bounds, showing our algorithm is either optimal or almost optimal in most settings. Numerical experiments demonstrate the superior performance of our algorithm.
This paper aims to achieve precise identification of diseases and pests affecting pear trees through the integration of YOLOv5, Jetson Nano, big data, and deep learning techniques. The objective is to facilitate timel...
详细信息
ISBN:
(纸本)9798400709630
This paper aims to achieve precise identification of diseases and pests affecting pear trees through the integration of YOLOv5, Jetson Nano, big data, and deep learning techniques. The objective is to facilitate timely detection of these issues, thereby enabling early prevention and control measures for pear tree health. The study employs YOLOv5 as the primary model, which is implemented on the embedded device jetson Nano. By leveraging the GPU parallelprocessing capabilities of jetson Nano's deep learning framework, this approach enhances picture analysis and detection speed while improving quality and efficiency. [1] Furthermore, it integrates big data with deep learning methodologies to bolster the accuracy of disease detection and identification. Utilizing these advanced technologies allows for accurate recognition of diseases and pests associated with pear trees through image analysis. This significantly reduces both the complexity involved in detecting such conditions and lowers operational thresholds for practitioners in the field. In comparison to traditional detection methods, YOLOvI technology exhibits no stringent requirements regarding environmental conditions or backgrounds;thus, it remains less susceptible to variations caused by weather factors making it a superior choice for pest and disease detection in agricultural settings.
Inflammatory Bowel Disease (IBD) is a global chronic intestinal inflammatory disease, and its incidence rate increases year by year with the progress of economic globalization. Currently, the diagnosis of IBD in child...
详细信息
ISBN:
(纸本)9798350385731;9798350385724
Inflammatory Bowel Disease (IBD) is a global chronic intestinal inflammatory disease, and its incidence rate increases year by year with the progress of economic globalization. Currently, the diagnosis of IBD in children mainly relies on endoscopic examination, but scoring endoscopic images is a challenging issue, especially in distinguishing different types of ulcers. To address this issue, this article designs a mobile application to accelerate data annotation processing and may provide reference for other unlabeled datasets. In the context of image segmentation, blurring labels has become an important issue. Deep learning methods are widely used in medical image segmentation, but their accuracy depends on high-quality annotated data. However, there are low-quality noise areas in the annotated data, and obtaining accurate and high-quality annotations becomes more time-consuming with limited annotation budgets. This article proposes a collaborative training framework to improve learning of noisy pixels. This framework determines the label confidence of an image by calculating the similarity between image pixels and surrounding pixels. Then, two parallel deep networks were constructed for semantic prediction, which aimed to guide each other on pixels that may have noise. By applying consistency in dual network prediction, the semantic information of uncertain pixels is corrected as much as possible. Experimental results have shown that this framework is slightly superior to models trained with pixel level precise labels, thus more effectively utilizing existing annotated data in the case of fuzzy labels.
This paper proposes a fluid rendering pipeline that uses OpenGL-4 shaders to employ the parallelprocessing capabilities of the GPU. The fluid's surface mesh is produced using tessellation shader stages where the ...
详细信息
In video super-resolution reconstruction, traditional methods often fall short in capturing details, particularly in edges and occluded areas, which affects the realism and clarity of the images. To address this issue...
详细信息
ISBN:
(纸本)9789819785070;9789819785087
In video super-resolution reconstruction, traditional methods often fall short in capturing details, particularly in edges and occluded areas, which affects the realism and clarity of the images. To address this issue, we propose a novel model-the Residual Hybrid Attention-Enhanced Video Super-Resolution Model, augmented by Cross Convolution techniques, denoted as RCVSR. The model ingeniously integrates a residual hybrid attention mechanism, refining the learning of global and local features through parallel channel attention and self-attention mechanisms. Simultaneously, our model introduces overlapping cross-attention blocks to enhance dynamic interactions between frames, thereby boosting the model's performance. Furthermore, the design of the cross-convolution blocks allows for parallelprocessing of vertical and horizontal gradient information in images, effectively extracting edge details. In multiple benchmark tests, the RCVSR model demonstrated its excellent reconstruction effects and outstanding performance.
image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignm...
详细信息
ISBN:
(数字)9798331515966
ISBN:
(纸本)9798331515973
image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processingimages, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method.
Innovations in powerful high-performance computing (HPC) architecture are enabling high-fidelity whole-core neutron transport simulations at reasonable time. Especially, the currently fashionable heterogeneous archite...
详细信息
The extensive instruction-set for deep learning (DL) significantly enhances the performance of general-purpose architectures by exploiting data-level parallelism. However, it is challenging to design arithmetic units ...
详细信息
ISBN:
(纸本)9783031396977;9783031396984
The extensive instruction-set for deep learning (DL) significantly enhances the performance of general-purpose architectures by exploiting data-level parallelism. However, it is challenging to design arithmetic units capable of performing parallel operations on a wide range of formats to perform DL instructions (DLIs) efficiently. This paper presents a multi-level parallel arithmetic architecture capable of supporting intra- and inter-operation parallelism for integer and a wide range of FP formats. For intra-operation parallelism, the proposed architecture supports multi-term dot-product for integer, half-precision, and Brain-Float16 formats using mixed-precision methods. For inter-operation parallelism, a dual-path execution is enabled to perform integer dot-product and single-precision (SP) addition in parallel. Moreover, the architecture supports the commonly used fused multiply-add (FMA) operations in general-purpose architectures. The proposed architecture strictly adheres to the computing requirements of DLIs and can efficiently implement them. When using benchmarked DNN inference applications where both integer and FP formats are needed, the proposed architecture can significantly improve performance by up to 15.7% compared to a single-path implementation. Furthermore, compared with state-of-the-art designs, the proposed architecture achieves higher energy efficiency and works more efficiently in implementing DLIs.
An increasing number of people are experiencing skin problems, and it is never easy for a clinician to make a correct diagnosis. One potential solution to these problems is the use of deep learning for skin disease di...
详细信息
The median filter is a simple yet powerful noise reduction technique that is extensively applied in image, signal, and speech processing. It can effectively remove impulsive noise while preserving the content of the i...
详细信息
The median filter is a simple yet powerful noise reduction technique that is extensively applied in image, signal, and speech processing. It can effectively remove impulsive noise while preserving the content of the image by taking the median of neighboring pixels;thus, it has various applications, such as restoration of a damaged image and facial beautification. The median filter is typically implemented in one of two major approaches: the histogram-based method, which requires O(1) computation time per pixel when focusing on the kernel radius r, and the sorting-based method, which requires approximately O(r(2)) computation time per pixel but has a light constant factor. These are used differently depending on the kernel radius and the number of bits in the image. However, the computation time is still slow, particularly when the kernel radius is in the mid to large range. This paper introduces novel and efficient median filter with constant complexity O(1) for kernel size using the wavelet matrix data structure, which has been applied to query-based searches on one-dimensional data. We extended the original wavelet matrix to two-dimensional data for application to computer graphics problems. The objective of this study was to achieve high-speed median filter computation in parallel computing environment with many threads (i.e., GPUs). Our implementation for the GPU is an order of magnitude faster than the histogram method for 8-bit images. Unlike traditional histogram methods, which suffer from significant computational overhead, the proposed method can handle images with high pixel depth (e.g., 16- and 32-bit high dynamic range images). When the kernel radius is greater than 12 for 8-bit images, the proposed method outperforms the other median filter computation methods.
暂无评论