Pixel-level structure segmentations have attracted considerable attention,playing a crucial role in autonomous driving within the metaverse and enhancing comprehension in light field-based machine ***,current light fi...
详细信息
Pixel-level structure segmentations have attracted considerable attention,playing a crucial role in autonomous driving within the metaverse and enhancing comprehension in light field-based machine ***,current light field modeling methods fail to integrate appearance and geometric structural information into a coherent semantic space,thereby limiting the capability of light field transmission for visual *** this paper,we propose a general light field modeling method for pixel-level structure segmentation,comprising a generative light field prompting encoder(LF-GPE)and a prompt-based masked light field pretraining(LF-PMP)*** LF-GPE,serving as a light field backbone,can extract both appearance and geometric structural cues *** aligns these features into a unified visual space,facilitating semantic ***,our LF-PMP,during the pretraining phase,integrates a mixed light field and a multi-view light field *** prioritizes considering the geometric structural properties of the light field,enabling the light field backbone to accumulate a wealth of prior *** evaluate our pretrained LF-GPE on two downstream tasks:light field salient object detection and semantic *** results demonstrate that LF-GPE can effectively learn high-quality light field features and achieve highly competitive performance in pixel-level segmentation tasks.
In recent years, significant progress has been made in salient object detection. Nevertheless, there remains a need for further improvements in the effective combination of local and global perspectives. Combining glo...
详细信息
Studies have shown that deep neural networks(DNNs) are vulnerable to adversarial examples(AEs) that induce incorrect behaviors. To defend these AEs, various detection techniques have been developed. However, most of t...
详细信息
Studies have shown that deep neural networks(DNNs) are vulnerable to adversarial examples(AEs) that induce incorrect behaviors. To defend these AEs, various detection techniques have been developed. However, most of them only appear to be effective against specific AEs and cannot generalize well to different AEs. We propose a new detection method against AEs based on the maximum channel of saliency maps(MCSM). The proposed method can alter the structure of adversarial perturbations and preserve the statistical properties of images at the same time. We conduct a complete evaluation on AEs generated by 6 prominent adversarial attacks on the Image Net large scale visual recognition challenge(ILSVRC) 2012 validation sets. The experimental results show that our method performs well on detecting various AEs.
As an extended computing paradigm of cloud computing, Mobile Edge Computing (MEC) facilitates real-time service responses by deploying resources near network edges. However, services should frequently move among multi...
详细信息
With the number of users that use mobile devices for frequent transactions increasing rapidly, it is a great challenge to guarantee the credibility of transactions. Blockchain is regarded as a practical technology for...
详细信息
Unsupervised image-to-image translation is a challenging task for computervision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only f...
详细信息
Unsupervised image-to-image translation is a challenging task for computervision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only focused on image-level translation but ignored image features processing, which led to a certain semantics loss, such as the changes of the background of the generated image, partial transformation, and so on. In this work, we propose a method of image-to-image translation based on generative adversarial nets(GANs). We use autoencoder structure to extract image features in the generator and add semantic consistency loss on extracted features to maintain the semantic consistency of the generated image. Self-attention mechanism at the end of generator is used to obtain long-distance dependency in image. At the same time, as expanding the convolution receptive field, the quality of the generated image is enhanced. Quantitative experiment shows that our method significantly outperforms previous works. Especially on images with obvious foreground, our model shows an impressive improvement.
Federated learning(FL)， as a distributed learning paradigm， allows multiple medical institutions to collaborate on learning without the need to centralize all client data. However， existing methods pay little atten...
Federated learning(FL)， as a distributed learning paradigm， allows multiple medical institutions to collaborate on learning without the need to centralize all client data. However， existing methods pay little attention to more challenging medical image semantic segmentation tasks， especially in the scenario of the imbalanced dataset in federated few-shot learning. In this paper， we propose a subnetwork-based federated few-shot organ image segmentation method. Firstly， individual clients train using local training samples and then upload local model gradients to the server. The server utilizes their respective local model gradients to update the subnetwork maintained on the server and generate aggregation weights for forming personalized model parameters. Through this method， we can learn the similarities between different clients to address data heterogeneity issues. In addition， to enhance the communication efficiency between clients and the server， we have also designed a personalized layer aggregation strategy， which only transmits partial layer model parameters during the communication process to improve communication efficiency. Finally， we conducted experiments on ABD-MRI and ABD-CT datasets to demonstrate the effectiveness of our method.
The segmentation of power lines in drone images is one of the challenging tasks in the field of computervision. Although power lines share the same difficulties with tiny object segmentation, occupying only a very sm...
详细信息
A large mode area multi-core orbital angular momentum(OAM)transmission fiber is designed and optimized by neural network and optimization *** neural network model has been established first to predict the optical prop...
详细信息
A large mode area multi-core orbital angular momentum(OAM)transmission fiber is designed and optimized by neural network and optimization *** neural network model has been established first to predict the optical properties of multi-core OAM transmission fibers with high accuracy and speed,including mode area,nonlinear coefficient,purity,dispersion,and effective index *** the trained neural network model is combined with different particle swarm optimization(PSO)algorithms for automatic iterative optimization of multi-core structures *** to the structural advantages of multi-core fiber and the automatic optimization process,we designed a number of multi-core structures with high OAM mode purity(>95%)and ultra-large mode area(>3000µm^(2)),which is larger by more than an order of magnitude compared to the conventional ring-core OAM transmission fibers.
作者：
Han, FeiZhang, YaoZhao, MengTianjin University of Technology
Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System of Ministry of Education Tianjin300384 China
As an emerging distributed machine learning paradigm, federated learning (FL) only shares model updates between clients and servers, and training data are secured on each client's device. Due to local data privacy...
详细信息
暂无评论