检索结果-内蒙古大学图书馆

Saliency Detection From Complex Background with Attention-Based Boundary-Aware Pyramid Pooling Network

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Fang, Jinsheng Tao, Yuhao Zhu, Gupei School of Computer Science and Engineering Minnan Normal University Zhangzhou China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou China

Deep convolution network have been widely adopted in saliency detection in recent years and achieved state-of-the-art performance. A central issue for previous methods is the limited capability of detecting objects that are overwhelmed by complex background. Aim to address this problem, we propose a novel attention-based boundary-aware pyramid pooling network, namely ABAPNet, which consists of feature aggregation module, pyramid pooling module and cascading dual attention module. The proposed ABAPNet method transits high-level information to shallow layers to keep transferring important features between layers and obtains more semantic features. Hybrid loss by fusing binary cross entropy (BCE), structural similarity (SSIM) and intersection-over-union (IOU) is employed to reduce the gradient of mixed loss of network output features, which guides the network to better segment boundaries from complex background. Experimental results on 5 public datasets show that the proposed ABAPNet outperforms the competitors. © 2022, The Authors. All rights reserved.

关键词： Object detection

Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Yang Liu, Qi Wu, Likang Yu, Runlong Yu, Sanshi Lei Zhang, Zaixi Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China

Federated recommendation (FedRec) can train personalized recommenders without collecting user data, but the decentralized nature makes it susceptible to poisoning attacks. Most previous studies focus on the targeted attack to promote certain items, while the untargeted attack that aims to degrade the overall performance of the FedRec system remains less explored. In fact, untargeted attacks can disrupt the user experience and bring severe financial loss to the service provider. However, existing untargeted attack methods are either inapplicable or ineffective against FedRec systems. In this paper, we delve into the untargeted attack and its defense for FedRec systems. (i) We propose ClusterAttack, a novel untargeted attack method. It uploads poisonous gradients that converge the item embeddings into several dense clusters, which make the recommender generate similar scores for these items in the same cluster and perturb the ranking order. (ii) We propose a uniformity-based defense mechanism (UNION) to protect FedRec systems from such attacks. We design a contrastive learning task that regularizes the item embeddings toward a uniform distribution. Then the server filters out these malicious gradients by estimating the uniformity of updated item embeddings. Experiments on two public datasets show that ClusterAttack can effectively degrade the performance of FedRec systems while circumventing many defense methods, and UNION can improve the resistance of the system against various untargeted attacks, including our ClusterAttack. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

Teaching resource recommendation for OBE based on kernel canonical correlation analysis

学校读者我要写书评

暂无评论

Teaching resource recommendation for OBE based on kernel can...

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Wu Changqian Li Shaozi Lin Yaojin Yu Xiehua Key Laboratory of Big Data and Artificial Intelligence in University of Fujian Province MinNan Science and Technology University José Rizal University Quanzhou China School of Informatics Xiamen University Xiamen China School of Computer Science Lab of Data Science and Intelligence Application Minnan Normal University Zhangzhou China Key Laboratory of Big Data and Artificial Intelligence in University of Fujian Province MinNan Science and Technology University Quanzhou China

data mining is used to extract information from OBE teaching resources, then the teaching resources and user personality database are established to improve the effectiveness of resources recommendation on the online learning platform. The properties of teaching resources and user personality traits are analyzed using the kernel canonical correlation analysis algorithm, and teaching materials with a high correlation coefficient are chosen to recommend to users. The simulation results demonstrate that this proposed method has higher accuracy and more accurate recommended resources when compared to the widely used teaching resource recommendation techniques.

关键词： Correlation coefficient Correlation databases Simulation Education data mining Kernel

SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yunchen Yu, Zhou He, Gaoqi Shen, Yunhang Li, Ke Sun, Xing Lin, Shaohui East China Normal University China Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education China Youtu Lab Tencent Shanghai China

Symmetric positive definite (SPD) matrices have shown important value and applications in statistics and machine learning, such as FMRI analysis and traffic prediction. Previous works on SPD matrices mostly focus on discriminative models, where predictions are made directly on E(X|y), where y is a vector and X is an SPD matrix. However, these methods are challenging to handle for large-scale data, as they need to access and process the whole data. In this paper, inspired by denoising diffusion probabilistic model (DDPM), we propose a novel generative model, termed SPD-DDPM, by introducing Gaussian distribution in the SPD space to estimate E(X|y). Moreover, our model is able to estimate p(X) unconditionally and flexibly without giving y. On the one hand, the model conditionally learns p(X|y) and utilizes the mean of samples to obtain E(X|y) as a prediction. On the other hand, the model unconditionally learns the probability distribution of the data p(X) and generates samples that conform to this distribution. Furthermore, we propose a new SPD net which is much deeper than the previous networks and allows for the inclusion of conditional factors. Experiment results on toy data and real taxi data demonstrate that our models effectively fit the data distribution both unconditionally and unconditionally and provide accurate predictions. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

Affine Equivariant Networks Based on Differential Invariants

学校读者我要写书评

暂无评论

Affine Equivariant Networks Based on Differential Invariants

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yikang Li Yeqing Qiu Yuxuan Chen Lingshen He Zhouchen Lin National Key Lab of General AI School of Intelligence Science and Technology Peking University The Chinese University of Hong Kong Shenzhen Shenzhen Research Institute of Big Data Institute for Artificial Intelligence Peking University Peng Cheng Laboratory

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Convolutional neural networks benefit from translation equivariance, achieving tremendous success. Equivariant networks further extend this property to other transformation groups. However, most existing methods require dis-cretization or sampling of groups, leading to increased model sizes for larger groups, such as the affine group. In this paper, we build affine equivariant networks based on differential invariants from the viewpoint of symmetric PDEs, without discretizing or sampling the group. To ad-dress the division-by-zero issue arising from fractional dif-ferential invariants of the affine group, we construct a new kind of affine invariants by normalizing polynomial relative differential invariants to replace classical differential invariants. For further flexibility, we design an equivariant layer, which can be directly integrated into convolutional networks of various architectures. Moreover, our frame-work for the affine group is also applicable to its continu-ous subgroups. We implement equivariant networks for the scale group, the rotation-scale group, and the affine group. Numerical experiments demonstrate the outstanding performance of our framework across classification tasks involving transformations of these groups. Remarkably, under the out-of-distribution setting, our model achieves a 3.37% im-provement in accuracy over the main counterpart affConv on the affNIST dataset.

关键词： Manifolds Computer vision Three-dimensional displays Accuracy Lie groups Polynomials Pattern recognition

WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ning, Kangyun Su, Yisong Lv, Xueqiang Zhang, Yuanzhe Liu, Jian Liu, Kang Xu, Jinan Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China College of Computer and Data Science Fuzhou University China The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation CAS China

Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align with real-world situations, where the necessity for tools is uncertain, and incorrect or unnecessary use of tools can damage the general abilities of LLMs. Therefore, we propose to explore whether LLMs can discern their ability boundaries and use tools flexibly. We then introduce the Whether-or-not tool usage Evaluation benchmark (WTU-Eval) to assess LLMs with eleven datasets, where six of them are tool-usage datasets, and five are general datasets. LLMs are prompted to use tools according to their needs. The results of eight LLMs on WTU-Eval reveal that LLMs frequently struggle to determine tool use in general datasets, and LLMs’ performance in tool-usage datasets improves when their ability is similar to ChatGPT. In both datasets, incorrect tool usage significantly impairs LLMs’ performance. To mitigate this, we also develop the finetuning dataset to enhance tool decision-making. Fine-tuning Llama2-7B results in a 14% average performance improvement and a 16.8% decrease in incorrect tool usage. We will release the WTU-Eval benchmark. © 2024, CC BY.

关键词： Decision making

DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets

学校读者我要写书评

暂无评论

DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haiyang Wang Chen Shi Shaoshuai Shi Meng Lei Sen Wang Di He Bernt Schiele Liwei Wang Center for Data Science Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Max Planck Institute for Informatics Saarland Informatics Campus Zhejiang Lab Huawei

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution, the attention mechanism in Transformers is more appropriate for flexibly modeling long-range relationships and is easier to be deployed in real-world applications. However, due to the sparse characteristics of point clouds, it is non-trivial to apply a standard transformer on sparse points. In this paper, we present Dynamic Sparse Voxel Transformer (DSVT), a single-stride window-based voxel Transformer backbone for outdoor 3D perception. In order to efficiently process sparse points in parallel, we propose Dynamic Sparse Window Attention, which partitions a series of local regions in each window according to its sparsity and then computes the features of all regions in a fully parallel manner. To allow the cross-set connection, we design a rotated set partitioning strategy that alternates between two partitioning configurations in consecutive self-attention layers. To support effective downsampling and better encode geometric information, we also propose an attention-style 3D pooling module on sparse points, which is powerful and deployment-friendly without utilizing any customized CUDA operations. Our model achieves state-of-the-art performance with a broad range of 3D perception tasks. More importantly, DSVT can be easily deployed by TensorRT with real-time inference speed (27Hz). Code will be available at https://***/Haiyang-W/DSVT.

关键词：

Large-Scale OD Matrix Estimation with A Deep Learning Method

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xiong, Zheli Lian, Defu Chen, Enhong Chen, Gang Cheng, Xiaomin The School of Data Science University of Science and Technology of China Anhui Hefei230000 China The Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China The Yangtze River Delta Information Intelligence Innovation Research Institute China

The estimation of origin-destination (OD) matrices is a crucial aspect of Intelligent Transport Systems (ITS). It involves adjusting an initial OD matrix by regressing the current observations like traffic counts of road sections (e.g., using least squares). However, the OD estimation problem lacks sufficient constraints and is mathematically underdetermined. To alleviate this problem, some researchers incorporate a prior OD matrix as a target in the regression to provide more structural constraints. However, this approach is highly dependent on the existing prior matrix, which may be outdated. Others add structural constraints through sensor data, such as vehicle trajectory and speed, which can reflect more current structural constraints in real-time. Our proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. This approach combines the advantages of both deep learning and numerical optimization algorithms. The neural network(NN) learns to infer structural constraints from probe traffic flows, eliminating dependence on prior information and providing real-time performance. Additionally, due to the generalization capability of NN, this method is economical in engineering. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset. Subsequently, we verified the stability of our method on real traffic data. Our experiments provided confirmation of the benefits of combining NN and numerical *** Codes I.2.1 Copyright © 2023, The Authors. All rights reserved.

关键词： Statistical tests

Attribute-based Message Recovery Designated Verifier Proxy Signature Scheme in Telemedicine System

学校读者我要写书评

暂无评论

Journal of Network Intelligence

Journal of Network intelligence 2022年第1期7卷 101-113页

作者： Hu, Yu Zhang, Yi-Fan Huang, Hui Zhou, Yu-Ping School of Computer Science Minnan Normal University Zhangzhou363000 China School of Computer Science Minnan Normal University Key Laboratory of Data Science and Intelligence Application Fujian Province University Zhangzhou363000 China

With the promotion of cloud medical diagnostic applications, the telemedicine system has become increasingly mature, which brings about much convenience to the people’s lives. Meanwhile, the diagnostic time was greatly reduced. Due to telemedicine system usually involves the sensitive information of users, the privacy issue is urgently to be solved. In order to solve the above problem, an attribute-based designated verifier proxy signature scheme, combined with message recovery, is proposed for the telemedicine system. A proxy delegation is designed to allow the proxy signer to obtain the same signing capacity as the original signer, the attribute-based fine-grained access control is also present to enable the valid verification of the signature and recovery of data. In addition, the scheme achieves unforgeability of signature and can resist the chosen message attack in Random Oracle Model. The comparisons of performance analysis demonstrates that the scheme is efficient in signing and verification phases. Therefore, it could be well appropriate for telemedicine system. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Diagnosis