With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to...
详细信息
With the rise of Foundation models, Text-to-image models, as one of its important branches, have been increasingly applied. While focusing on the impressive generation capabilities of these models, it is also crucial ...
详细信息
Face aging has attracted widespread attention in recent years, but most studies are based on the same emotional situation. Is the same person's aging in different emotional situations the same? To solve the above ...
详细信息
Face aging has attracted widespread attention in recent years, but most studies are based on the same emotional situation. Is the same person's aging in different emotional situations the same? To solve the above confusion, this paper proposes a novel face aging model DEF-Net, which consists of two parts: different emotional learnings (Emotion-Net) and face aging (Age-Net). Given a target emotion category, DEF-Net first assists the image from the original dataset to learn the emotion features through Emotion-Net and the generated dataset is used as the inputs of Age-Net. At the same time, multiple loss functions are used to ensure that the crucial information of the original image is not lost. Secondly, Age-Net, which has been pre-trained on the original dataset, began to adopt the generated dataset to learn the aging distribution under different emotions. Designed loss functions are utilized to ensure that the realistic target images generated by Age-Net do not lose the learned emotional characteristics. Finally, extensive experiments are used to verify the performance of DEF-Net. Compared with other state-of-the-art methods: (1) DEF-Net can learn different facial emotions across different datasets and generate corresponding realistic aging images;(2) the results achieved by our DEF-Net are demonstrated to be better than those by the model that performs face aging first and then learns different emotional characteristics.
Reconstructing the damaged images with perspective views has an extensive range in the field of image inpainting. However, most existing methods generated inadequately realistic restored images. Accomplishing this pro...
详细信息
image enhancement is a process to improve the visual standard of image so as to extract spatial features of image. Histogram Equalization is method by which image can be improved for better perception and interpretati...
详细信息
Existing image inpainting methods used traditional and deep learning methods to restore a large missing region in the damaged image. This often leads to color discrepancy and blurriness. Pre-processing of prior line d...
详细信息
Convolutional Neural Network (CNN) and Transformer architectures have been extensively applied in the domain of remote sensing image super-resolution. However, to achieve optimal performance, many existing methods are...
详细信息
ISBN:
(数字)9798331509712
ISBN:
(纸本)9798331509729
Convolutional Neural Network (CNN) and Transformer architectures have been extensively applied in the domain of remote sensing image super-resolution. However, to achieve optimal performance, many existing methods are designed with a large number of parameters, thereby increasing the complexity of the model and hindering practical deployment. To address this issue, we propose an innovative model that synergizes CNN and Transformer architectures while employing a minimal number of their respective modules. This approach significantly reduces the parameter count while maintaining superior performance. Firstly, by constructing additional shallow feature representations as input, we enhance the feature extraction capabilities for individual images. Secondly, we utilize residual connections between various modules to integrate multi-scale, high-dimensional feature information, thus ensuring efficient transmission. Finally, the image reconstruction module is employed to restore the high-resolution image. Experimental results show that FCTNet significantly outperforms existing methods while maintaining a substantially lower parameter count, as demonstrated through evaluations on two public datasets.
作者:
Yu, JingyaWang, GuoyouCheng, ShenghuaSchool of Automation
Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multispectral Information Processing Wuhan China Britton Chance Center
School of Engineering Sciences Huazhong University of Science and Technology Moe Key Laboratory for Biomedical Photonics Wuhan China
Liquid-based thin-layer cell smears are very important for the early screening and prevention of cervical cancer, and computer-aided diagnosis can reduce the workload of pathologists. The cell classification method ba...
详细信息
While petabytes of data are generated each day by a number of independent computing devices, only a few of them can be finally collected and used for deep learning (DL) due to the apprehension of data security and pri...
详细信息
While petabytes of data are generated each day by a number of independent computing devices, only a few of them can be finally collected and used for deep learning (DL) due to the apprehension of data security and privacy leakage, thus seriously retarding the extension of DL. In such a circumstance, federated learning (FL) was proposed to perform model training by multiple clients' combined data without the dataset sharing within the cluster. Nevertheless, federated learning with periodic model averaging (FedAvg) introduced massive communication overhead as the synchronized data in each iteration is about the same size as the model, and thereby leading to a low communication efficiency. Consequently, variant proposals focusing on the communication rounds reduction and data compression were proposed to decrease the communication overhead of FL. In this article, we propose Overlap-FedAvg, an innovative framework that loosed the chain-like constraint of federated learning and paralleled the model training phase with the model communication phase (i.e., uploading local models and downloading the global model), so that the latter phase could be totally covered by the former phase. Compared to vanilla FedAvg, Overlap-FedAvg was further developed with a hierarchical computing strategy, a data compensation mechanism, and a nesterov accelerated gradients (NAG) algorithm. In Particular, Overlap-FedAvg is orthogonal to many other compression methods so that they could be applied together to maximize the utilization of the cluster. Besides, the theoretical analysis is provided to prove the convergence of the proposed framework. Extensive experiments conducting on both image classification and natural language processing tasks with multiple models and datasets also demonstrate that the proposed framework substantially reduced the communication overhead and boosted the federated learning process.
Deep learning techniques such as convolutional neural networks (CNNs) have been used in a wide range of fields due to their superior performance, e.g., image classification, autonomous driving and natural language pro...
详细信息
Deep learning techniques such as convolutional neural networks (CNNs) have been used in a wide range of fields due to their superior performance, e.g., image classification, autonomous driving and natural language processing. However, recent progress shows that deep learning models are vulnerable to adversarial samples, which are crafted by adding small perturbations on normal samples that are imperceptible to human beings but can mislead the deep learning models to output incorrect results. Many adversarial attack models are proposed and many adversarial detection methods are developed to detect adversarial samples generated by these attack models. However, the evaluations of these detection methods are fragmented and scatter in separate literature, and the community still lacks a comprehensive understanding of the ability and performance of existing adversarial detection methods when facing different attack models on different datasets. In this paper, by using image classification as the example application scenario, we conduct a comprehensive study on the performance of five mainstream adversarial detection methods against five major attack models on four widely used benchmark datasets. We find that the detection accuracy of different methods interleaves for different attack models and dataset. Moreover, besides detection accuracy, we also evaluate the time efficiency of different detection methods. The findings reported in this paper can provide useful insights when designing systems to detect adversarial samples and act as a guideline to design new methods to detect adversarial samples.
暂无评论