检索结果-内蒙古大学图书馆

Vision-Based Fruit Recognition Via Multi-Scale Attention Cnn

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Min, Weiqing Wang, Zhiling Yang, Jiahao Liu, Chunlin Jiang, Shuqiang The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Fruit quality assessment, grading and sorting are of vital importance to fruit processing, and all these involve fruit recognition. Vision-based fruit recognition can recognize fruit automatically and further support more applications such as fruit-picking robots, self-checkout service, and dietary guidance. Recent works resort to Convolutional Neural Networks (CNNs) for vision-based fruit recognition because of their powerful expressive capacity. However, most works simply utilize existing CNNs and ignore characteristics of fruit images, resulting in sub-optimal recognition performance. To solve this problem, we adopt a Multi-Scale Attention Network (MSANet), which explores attention from different layers of CNNs and aggregates various visual attentional features from different levels into final comprehensive representations. Extensive evaluations on four fruit benchmark datasets demonstrate that the method achieves state-of-the-art recognition performance. In addition, we report various experimental results from different deep networks as baselines. Codes and models will be released upon publication. Models and code are available at http://123.57.42.89/codes/***. © 2022, The Authors. All rights reserved.

关键词： Computer vision

SFTA: Spiking Neural Networks Vulnerable to Spiking Feature Transferable Attack

学校读者我要写书评

暂无评论

SFTA: Spiking Neural Networks Vulnerable to Spiking Feature ...

IEEE International Symposium on Parallel and Distributed processing with Applications and IEEE International Conference on Ubiquitous computing and Communications (ISPA/IUCC)

作者： Xuanwei Lin Chen Dong Ximeng Liu College of Computer and Data Science Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University) Key Lab of Information Security of Network Systems (Fuzhou University)

Many recent works have shown that spiking neural networks (SNNs) are vulnerable to well-crafted adversarial attacks in the white-box setting, which may lead to misclassification of the trained model. However, the information about the model is in a black-box setting and is usually unknown to the attacker, e.g., the parameters and structure of the model. So it is more challenging to counter the attack in the black-box setting, and there is still little research on this aspect in SNNs. Therefore, this work describes a transfer-based black box adversarial attack against spike feature space representations, providing insights for robust spike features in SNNs models. The attack is explicitly designed to be transferable, and more robust feature gradients are obtained by accumulating the feature gradients of the intermediate layers. Then we can successfully attack the black-box model by suppressing robust positive features and enhancing negative features. Extensive experimental evaluation demonstrates the proposed method’s effectiveness and superior performance on static and neuromorphic datasets. i.e., The attack success is 89.72% and 90% on the static MNIST and CIFAR10 datasets, and 85.97% and 69.09% on the neuromorphic N-MNIST and CIFARO-DVS datasets.

关键词： Correlation Neuromorphics Neural networks Closed box Ubiquitous computing Optimization Glass box

Enhancing Sample Utilization in Noise-robust Deep Metric Learning with Subgroup-based Positive-pair Selection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yu, Zhipeng Xu, Qianqian Jiang, Yangbangyan Sun, Yingfei Huang, Qingming The School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive pairs for noisy samples to enhance the sample utilization. Specifically, SGPS first effectively identifies clean and noisy samples by a probability-based clean sample selectionstrategy. To further utilize the remaining noisy samples, we discover their potential similar samples based on the subgroup information given by a subgroup generation module and then aggregate them into informative positive prototypes for each noisy sample via a positive prototype generation module. Afterward, a new contrastive loss is tailored for the noisy samples with their selected positive pairs. SGPS can be easily integrated into the training process of existing pair-wise DML tasks, like image retrieval and face recognition. Extensive experiments on multiple synthetic and real-world large-scale label noise datasets demonstrate the effectiveness of our proposed method. Without any bells and whistles, our SGPS framework outperforms the state-of-the-art noisy label DML methods. Code is available at https://***/smuelpeng/SGPS-NoiseFreeDML. © 2025, CC BY.

关键词： Contrastive Learning

Heterophilic Graph Representation Learning Based on Multi-Order Information Extraction and High and Low Pass Filters

学校读者我要写书评

暂无评论

Heterophilic Graph Representation Learning Based on Multi-Or...

Smart World Congress (SWC), IEEE

作者： Ling Wu Xinyu Li Yingjie Yang Kun Guo Qishan Zhang College of Computer and Data Science Fuzhou University Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China School of Computer Science and Informatics De Montfort University Leicester England College of Economics and Humanities Shanghai International Studies University Shanghai China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Real-world networks can be divided into homophilic and heterophilic graphs. Significantly, many nodes tend to be heterophilic in a homophilic graph. Graph representation learning in heterophilic graphs has attracted considerable significance in recent years as it breaks the homophily assumption and achieves higher-quality graph embeddings. However, existing heterophilic graph representation learning methods often mix attribute and topological information, neglecting the mutual exclusion between attribute information and topological information. Furthermore, algorithms in heterogeneous graphs usually rely on specific matrix structures to capture high-order information, which may restrict the applicability of these methods. To tackle these issues, this paper proposes a GNN-based strategy for Heterophilic graph Representation Learning based on Multi-order information extraction and High and Low pass filters (HRLMHL). First, we designed two relatively independent modules to learn attribute information and topological information, respectively, to address the issue of mismatch. Second, we built a multi-order information extraction module to extract multi-order similarity features, thereby achieving the learning of high-order graph information. Experiments on real datasets show that the node classification accuracy is superior to that of the state-of-the-art methods on most datasets.

关键词： Representation learning Accuracy Low-pass filters Information retrieval Feature extraction Graph neural networks Topology Data mining Unsupervised learning

Latent multi-view subspace clustering based on Laplacian regularized representation

学校读者我要写书评

暂无评论

Latent multi-view subspace clustering based on Laplacian reg...

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Wei Guo Hangjun Che Man-Fai Leung Nankun Mu Xiangguang Dai Yuming Feng School of Electronic and Information Engineering Southwest University Chongqing China School of Electronic Information Engineering Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Chongqing China School of Computing and Information Science Faculty of Science and Engineering Anglia Ruskin University Cambridge UK Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing China School of Computer Science and Engineering Chongqing Three Gorges University Chongqing China Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Chongqing China

We propose a latent multi-view subspace clustering model based on Laplacian regularized representation. To emphasize the information of the representation matrix at the local level and reflect the grouping effect of clustering, a Laplacian regularization is imposed on the representation matrix. Additionally, To boost the efficiency o f c lustering, we apply nonnegative constraints on the representation matrix. A unified framework is designed to solve the proposed model by using ALM and LADMAP methods. The proposed model has excellent performance, as demonstrated by a number of experimental findings.

关键词：

Sle Diagnosis Research Based on Sers Combined with a Multi-Modal Fusion Method

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Huang, Yuhao Chen, Chen Chang, Chenjie Cheng, Zhiyuan Liu, Yang Chen, Cheng Lv, Xiaoyi College of Software Xinjiang University Xinjiang Urumqi830046 China College of Information Science and Engineering Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi830046 China Xinjiang Cloud Computing Application Laboratory Xinjiang Cloud Computing Engineering Technology Research Center Karamay834000 China

As artificial intelligence technology gains widespread adoption in biomedicine, the exploration of integrating biofluidic Raman spectroscopy for enhanced disease diagnosis opens up new prospects for the practical application of Raman spectroscopy in clinical settings. However, for Systemic Lupus Erythematosus (SLE), the relatively weak signals from a single Raman spectroscopic data make it difficult to obtain desirable classification results. Although the surface enhancement technique can enhance the scattered signal of Raman spectroscopic data, the sensitivity of the SERS substrate to airborne impurities and the non-uniform distribution of hotspots degrade some of the signals. To fully utilize both types of data, this paper proposes a two-branch residual-attention network (DBRAN) fusion technique that allows the original spectra to complement the degraded portion, improving the model's classification accuracy. The residual module is used to extract features, which preserves the original features while extracting the deep ones. At the same time, the study incorporates the attention module in both the upper and lower branches to handle the weight assignment of the two modal features more efficiently. The experimental results demonstrated that both the low-level fusion method and the intermediate-level fusion method significantly improved the diagnostic accuracy of SLE disease classification when compared with a single modality, and the intermediate-level fusion DBRAN achieved 100% classification accuracy, sensitivity, and specificity. Compared with the raw Raman spectrum single mode and SERS single mode, the improvement is 10% and 7%, respectively. This experiment realized the rapid diagnosis of SLE disease by fusing the spectral data of multiple modes, which provides a reference idea in the Raman spectroscopy field. © 2023, The Authors. All rights reserved.

关键词： Raman spectroscopy

Scalable Graph Compressed Convolutions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Junshu Wang, Shuhui Yang, Chenxue Huang, Qingming The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The Agricultural Information Institute China Academy of Agricultural Sciences Beijing100081 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518066 China

Designing effective graph neural networks (GNNs) with message passing has two fundamental challenges, i.e., determining optimal message-passing pathways and designing local aggregators. Previous methods of designing optimal pathways are limited with information loss on the input features. On the other hand, existing local aggregators generally fail to extract multi-scale features and approximate diverse operators under limited parameter scales. In contrast to these methods, Euclidean convolution has been proven as an expressive aggregator, making it a perfect candidate for GNN construction. However, the challenges of generalizing Euclidean convolution to graphs arise from the irregular structure of graphs. To bridge the gap between Euclidean space and graph topology, we propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution. The permutations constrain all nodes in a row regardless of their input order and therefore enable the flexible generalization of Euclidean convolution to graphs. Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning. CoCN follows local feature-learning and global parameter-sharing mechanisms of convolution neural networks. The whole model can be trained end-to-end, with compressed convolution applied to learn individual node features and their corresponding structure features. CoCN can further borrow successful practices from Euclidean convolution, including residual connection and inception mechanism. We validate CoCN on both node-level and graph-level benchmarks. CoCN achieves superior performance over competitive GNN baselines. Codes are available at https://***/sunjss/CoCN. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

Uncertainty-boosted Robust Video Activity Anticipation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qi, Zhaobo Wang, Shuhui Zhang, Weigang Huang, Qingming The School of Computer Science and Technology Harbin Institute of Technology Weihai264209 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China

Video activity anticipation aims to predict what will happen in the future, embracing a broad application prospect ranging from robot vision and autonomous driving. Despite the recent progress, the data uncertainty issue, reflected as the content evolution process and dynamic correlation in event labels, has been somehow ignored. This reduces the model generalization ability and deep understanding on video content, leading to serious error accumulation and degraded performance. In this paper, we address the uncertainty learning problem and propose an uncertainty-boosted robust video activity anticipation framework, which generates uncertainty values to indicate the credibility of the anticipation results. The uncertainty value is used to derive a temperature parameter in the softmax function to modulate the predicted target activity distribution. To guarantee the distribution adjustment, we construct a reasonable target activity label representation by incorporating the activity evolution from the temporal class correlation and the semantic relationship. Moreover, we quantify the uncertainty into relative values by comparing the uncertainty among sample pairs and their temporal-lengths. This relative strategy provides a more accessible way in uncertainty modeling than quantifying the absolute uncertainty values on the whole dataset. Experiments on multiple backbones and benchmarks show our framework achieves promising performance and better robustness/interpretability. Source codes are available at https://***/qzhb/UbRV2A. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Some bounds on the cardinality of the b-symbol weight spectrum of codes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Hongwei Li, Shitao Shi, Minjia Xia, Shu-Tao Solé, Patrick Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China School of Mathematical Sciences Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China Centrale Marseille CNRS I2M Aix Marseille University Marseille13009 France State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China

The size of the Hamming distance spectrum of a code has received great attention in recent research. The main objective of this paper is to extend these significant theories to the b-symbol distance spectrum. We examine this question for various types of codes, including unrestricted codes, additive codes, linear codes, and cyclic codes, successively. For the first three cases, we determine the maximum size of the b-symbol distance spectra of these codes smoothly. For the case of cyclic codes, we introduce three approaches to characterize the upper bound for the cardinality of the b-symbol weight spectrum of cyclic codes, namely the period distribution approach, the primitive idempotent approach, and the b-symbol weight formula approach. As two by-products of this paper, the maximum number of symplectic weights of linear codes is determined, and a basic inequality among the parameters [n, k, dH(C)]q of cyclic codes is provided. © 2024, CC0.

关键词： Hamming distance