Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models ...
详细信息
The huge amount of data enforces great pressure on the processing efficiency of database systems. By leveraging the in-situ computing ability of emerging nonvolatile memory, processing-in-memory (PIM) technology shows...
详细信息
Nowadays, with advanced information technologies deployed citywide, large data volumes and powerful computational resources are intelligentizing modern city development. As an important part of intelligent transportat...
详细信息
FPGA has been considered as a promising solution to accelerate Convolutional Neural Networks (CNNs) for its excellent performance in energy efficiency and programmability. However, prior designs are usually designed f...
详细信息
Molecular docking is a crucial step in drug development, which enables the virtual screening of compound libraries to identify potential ligands that target proteins of interest. However, the computational complexity ...
详细信息
Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common...
详细信息
In this paper, a deep multi-kernel clustering network, named DMKCN, is proposed to learn a high-quality and structurally separable kernel representation for the clustering task. Specifically, a multi-kernel learner is...
In this paper, a deep multi-kernel clustering network, named DMKCN, is proposed to learn a high-quality and structurally separable kernel representation for the clustering task. Specifically, a multi-kernel learner is proposed to choose a suitable kernel function by learning a suitable combination of kernel functions automatically. A kernel-aid encoder module, consisting of a series of multi-kernel learners, is proposed to learn the structurally separable kernel representation. Besides, a dual self-supervised mechanism, consisting of a kernel self-supervised strategy and a representation self-supervised strategy, is designed to uniformly optimize the kernel representation learning and structural partition. The kernel self-supervised strategy is developed to supervise the multi-kernel learners with the consideration of an objective of clustering task, the representation self-supervised strategy is developed to guide the optimization of kernel representation learning by reconstructing the raw data. Extensive experiments on six real-world datasets demonstrate the outstanding performance of our proposed DMKCN.
Ultrasound images are vital for medical diagnostics but often suffer from information loss and blurred details due to limitations in imaging systems and sensor technologies. Many researchers have proposed super-resolu...
详细信息
ISBN:
(数字)9798350377613
ISBN:
(纸本)9798350377620
Ultrasound images are vital for medical diagnostics but often suffer from information loss and blurred details due to limitations in imaging systems and sensor technologies. Many researchers have proposed super-resolution algorithms to enhance medical images. But existing super-resolution methods struggle with the uneven distribution of noise and clarity. To address this, we propose a super-resolution algorithm for medical images based on multi-scale feature aggregation Leveraging the architecture of Unet as our primary framework, our method enhances output details through multi-scale hole convolutions. Taking into consideration the characteristics of ultrasonic images, we propose a frequency domain-based module to enhances edge information while effectively denoising the image. Furthermore, to improve the quality of the output images, we introduce an image processing module grounded in global information. The module ensures clarity while considering the overarching context, thereby preserving global consistency and enhancing output quality. We experiment on three datasets to demonstrate the effectiveness of our model. Additionally, significant improvements in medical image segmentation are observed, proving the practicability of our proposed approach.
Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of ...
Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of these techniques under communication constraints are not well-explored. This paper investigates the joint uplink compression problem in communication-constrained FL systems. We propose a Block-TopK sparsification scheme to reduce the proportion of bits used for locating entries of a sparsified vector. Considering the communication constraints, an optimization formulation is proposed to minimize the compression error. By solving the optimization problem, our joint compression method provides a better trade-off between sparsity budget and bit width. Numerical results demonstrate that our approach achieves 99.96% of baseline accuracy with only 1.56% of the baseline communication overhead when training ResNet-18 on CIFAR-10.
Deep learning (DL) systems usually utilize asynchronous prefetch to improve data reading performance. However, the efficiency of the data transfer path from hard disk to DRAM is still limited by disk performance. The ...
详细信息
暂无评论