检索结果-内蒙古大学图书馆

14th International Conference on Brain Inspired cognitive Systems, BICS 2024

作者： Zhang, Jingjing Wang, Huabin Shang, Dongxu Yuan, Hongrui Tao, Liang Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei 230601 China

ISBN: (纸本)9789819628810

Research on adversarial attacks for facial recognition identifies and mitigates vulnerabilities in facial recognition systems, enhancing their security. Current adversarial attacks targeting facial attributes lack precision in controlling specific attributes, often altering multiple facial features instead of a single target attribute. Such imprecise modifications reduce the attack’s effectiveness and stealthiness. To address these issues, this paper proposes a method for generating adversarial examples based on multi-layer feature map fusion. First, we design a framework called StarAdv, which uses fused multi-layer feature maps with high concealment to achieve realistic facial image transformations under different attributes. This approach generates adversarial images visually similar to the originals while possessing specific misleading properties, enabling transferable attacks on facial recognition systems. Second, we introduce a Multi-layer Fusion module that captures weight information from each layer of the network’s residual blocks to adaptively fuse feature maps from different layers, producing high-concealment feature maps. Finally, we propose a Bilinear Feature Map Interpolation (BFMI) algorithm to interpolate the high-concealment features with the original image features, ensuring the final decoded adversarial samples maintain a natural appearance, further reducing the likelihood of detection. We conduct comprehensive experiments on the CelebA dataset, demonstrating that the adversarial facial images generated by our method possess semantic plausibility and authenticity in appearance and achieve a high attack success rate in both white-box and black-box settings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial attack bilinear interpolation black-box transferability high camouflage multi-layer feature map fusion

来源：评论

学校读者我要写书评

暂无评论

Dynamic Prompt Adjustment for Multi-label Class-Incremental Learning 14th

Dynamic Prompt Adjustment for Multi-label Class-Incremental...

引用

14th International Conference on Brain Inspired cognitive Systems, BICS 2024

作者： Zhao, Haifeng Jin, Yuguang Ma, Leilei Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Anhui Hefei China School of Computer Science and Technology Anhui University Anhui Hefei China

ISBN: (纸本)9789819628810

Significant advancements have been made in single-label incremental learning (SLCIL), yet the more practical and challenging multi-label class-incremental learning (MLCIL) remains understudied. Recently, visual language models such as CLIP have achieved good results in classification tasks. However, directly using CLIP to solve MLCIL issue can lead to catastrophic forgetting. To tackle this issue, we integrate an improved data replay mechanism and prompt loss to curb knowledge forgetting. Specifically, our model enhances the prompt information to better adapt to multi-label classification tasks and employs confidence-based replay strategy to select representative samples. Moreover, the prompt loss significantly reduces the model’s forgetting of previous knowledge. Experimental results demonstrate that our method has substantially improved the performance of MLCIL tasks across multiple benchmark datasets, validating its effectiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data Replay Multi-Label Class Incremental Learning Prompt Regularization Prompt Tuning

来源：评论

学校读者我要写书评

暂无评论

Scene text detection based on progressive Multi-scale feature fusion and contextual information enhancement

Scene text detection based on progressive Multi-scale featur...

引用

2024 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2024

作者： Wang, Futian Xu, Guozhu School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China

ISBN: (纸本)9781510689275

Scene text detection draws more and more attention in recent years which targets detect the text regions in natural scenarios. It is still a challenging task in nowadays due to the influence of motion blur and scale variation. In this paper, we propose a novel scene text detection framework which well handle the small text detection in challenging scenarios. Specifically, given an input image, we first adopt a feature pyramid network to extract the deep features and feed them into a contextual information enhancement module for context information mining. Meanwhile, we also propose the progressive multi-scale feature fusion, multi-layer attention fusion module to aggregate multi-scale and local-global features. Finally, we concatenate all these features and feed them into an attention layer for segmentation map and threshold map prediction, thus, get the final detected texts. Extensive experiments fully validated the effectiveness of our proposed modules for accurate scene text detection. © 2025 SPIE.

关键词： Contextual Information Enhancement Feature Fusion Text Detection

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Graph Learning on Adaptive Mined key Frames for High-Performance Multi-Object Tracking 14th

Spatio-temporal Graph Learning on Adaptive Mined Key Frames...

引用

14th International Conference on Brain Inspired cognitive Systems, BICS 2024

作者： Wang, Futian Liu, Fengxiang Wang, Xiao School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China

ISBN: (纸本)9789819628841

In this work, we propose a novel adaptive key frame mining strategy to guide multi-object tracking, which combines the advantages of short-term and long-term correlation to capture both the structured spatial relationships between different objects as well as the temporal relationships of objects in different frames. We designed the KFE (key Frame Extraction) module to adaptively perform video segmentation using the reinforcement learning KFE module, which guides the tracker to mine the intrinsic logic of the video to make the correlation effect more significant. In video, mutual occlusion between objects frequently occurs, so the interactions between objects within frames cannot be ignored. Most of the current graph-based work utilizes the features of inter-frame objects for mutual fusion. Based on this, we design an IFF (intra-frame feature fusion) module that passes information between the target and the surrounding objects through GCN to make the target recognizable, thus solving the problem of tracking loss and similar appearance due to object occlusion. Our proposed tracker utilizes both long and short trajectories and takes into account the spatial relationship between objects while leveraging the intrinsic logic of the video clips, thus further improving the performance. It achieves impressive results: 68.6 HOTA, 81.0 IDF1, 66.6 AssA, and 893 IDS on the MOT17 dataset, proving its effectiveness and accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Intra-frame Feature Fusion Multi-Object Tracking Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

WFSS: weighted fusion of spectral transformer and spatial self-attention for robust hyperspectral image classification against adversarial attacks

引用

Visual Intelligence 2024年第1期2卷 1-16页

作者： Tang, Lichun Yin, Zhaoxia Su, Hang Lyu, Wanli Luo, Bin Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Anhui China School of Communication & Electronic Engineering East China Normal University Shanghai China Department of Computer Science and Technology Tsinghua University Beijing China

The emergence of adversarial examples poses a significant challenge to hyperspectral image (HSI) classification, as they can attack deep neural network-based models. Recent adversarial defense research tends to establish global connections of spatial pixels to resist adversarial attacks. However, it cannot yield satisfactory results when only spatial pixel information is used. Starting from the premise that the spectral band is equally important for HSI classification, this paper explores the impact of spectral information on model robustness. We aim to discover potential relationships between different spectral bands and establish global connections to resist adversarial attacks. We design a spectral transformer based on the transformer structure to model long-distance dependency relationships among spectral bands. Additionally, we use a self-attention mechanism in the spatial domain to develop global relationships among spatial pixels. Based on the above framework, we further explore the influence of both spectral and spatial domains on the robustness of the model against adversarial attacks. Specifically, a weighted fusion of spectral transformer and spatial self-attention (WFSS) is designed to achieve the multi-scale fusion of spectral and spatial connections, which further improves the model’s robustness. Comprehensive experiments on three benchmarks show that the WFSS framework has superior defensive capabilities compared to state-of-the-art HSI classification methods. © The Author(s) 2024.

关键词： Adversarial attack Adversarial example Hyperspectral image (HSI) classification Self-attention Transformer

来源：评论

学校读者我要写书评

暂无评论

From Image to the Ground: Recover the Ground Location of Vehicles from Traffic Cameras Using Neural Networks 14th

From Image to the Ground: Recover the Ground Location of Veh...

引用

14th International Conference on Brain Inspired cognitive Systems, BICS 2024

作者： Wang, Xuzhen Wang, Wenzhong Tang, Jin School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China

ISBN: (纸本)9789819628841

Robust estimation of on-road vehicle positions is important for traffic monitoring. We propose a neural network based approach to recover the ground locations of vehicles in traffic surveillance videos. We frame the location estimation problem as an object detection task. In contrast to the current state-of-the-art image object detection methods which only roughly estimate the object bounding boxes on the image plane, we aim to estimate the vehicle locations on the ground (the location in the frame of the road ground plane). In order to achieve this goal, we first transform the image into the bird’s eye view (BEV) image, and then detect the bounding box of vehicles in the BEV images. However, the BEV images exhibit severe distortions which hinders the detection accuracy significantly. Furthermore, the detections from consecutive images are inconsistent, i.e. the bounding boxes of the same vehicle in different images are of different sizes. To address these two challenges, we present a multi-task detection model which significantly boost the detection rate, and we design a novel consistency loss which constraints the size of detection boxes of identical vehicles to be the same. In order to effectively train and evaluate the model, we collect a dataset of traffic videos, which contains synchronous videos captured from both frontal view and bird’s eye view. Our experiments show that our multi-task detection model and consistency loss significantly improve the detection accuracy and stabilize detection results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Consistency Loss Multi-task Model Object Detection Vehicle Position Determination

来源：评论

学校读者我要写书评

暂无评论

STRNet: Semantic Segmentation Based on Small Target Refinement at Large Scale 24

STRNet: Semantic Segmentation Based on Small Target Refineme...

引用

3rd International Conference on Computer, Artificial Intelligence and Control Engineering, CAICE 2024

作者： Wang, Futian Shi, Tao Luo, Bin Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9798400716942

In the past few years, most high-performance semantic segmentation models have focused on learning semantic information in high-level semantic features, and in order to obtain more features, they will use high-resolution images for high-rate downsampling. Although this will obtain a better segmentation effect, due to the high rate of subsampling, the segmentation effect of small and medium-sized targets in the image is very poor, and because the training is conducted with high-resolution images, it will bring huge pressure on computing resources. To solve this problem, we propose a new two-branch small target refinement model (STRNet), and in order to reduce the high cost of computing resources brought by high resolution images, we use low resolution images for training. A large number of experiments demonstrated that our approach improved Cityscapes and CamVid datasets by 2.0% and 3.8% over the strong baseline, respectively. © 2024 ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

KDI-Net: dual-domain mapping network for undersampled magnetic resonance imaging reconstruction

KDI-Net: dual-domain mapping network for undersampled magnet...

引用

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Guo, Haiyang Zuo, Zhentao Sun, Dengdi Zhou, Tiangang AHU-IAI AI Joint Laboratory Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China State Key Laboratory of Brain and Cognitive Science Institute of Biophysics Chinese Academy of Sciences Beijing100101 China University of Chinese Academy of Sciences Beijing100049 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computing School of Artificial Intelligence Anhui University Hefei230601 China

ISBN: (纸本)9781510680425

Magnetic resonance imaging (MRI) is an imaging technique that provides comprehensive anatomical and functional information on the human body, but prolonged acquisition of fully sampled MRI images causes patient discomfort and motion *** recent years, deep learning (DL) has made significant progress in accelerating MRI image *** present, MRI image reconstruction is concentrated on single domain, but hybrid domain reconstruction has more ***, we propose a hybrid domain reconstruction method based on AUTOMAP-KDI-Net, which divided into three parts: K-Block, D-Block and *** evaluated the performance of our KDI-Net model for MRI image reconstruction using PSNR, RMSE, and SSIM metrics and three reduction factors (2, 3, 4) on two publicly available MRI datasets (the AUTOMAP brain dataset and the Calgary Campinas single-coil brain dataset).The results show that KDI-Net performs better than AUTOMAP and Complex *** to AUTOMAP, KDI-Net basically improved each metric by more than 6%.Compared to Complex AUTOMAP, KDI-Net basically improved by more than 8% on each *** reduction factor 2, the reconstructed MRI image is very close to ground *** specially designed KDI-Net can extract the sparsity from single channel MRI K-space, which achieve 2 folder acceleration. © 2024 SPIE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Deformation Field Component Attention Fusion for Coarse-to-Fine Medical Image Registration Network 9

Deformation Field Component Attention Fusion for Coarse-to-F...

引用

9th International Conference on Intelligent computing and Signal Processing, ICSP 2024

作者： Zhang, Chi Zhao, Haifeng Liu, Deyin School of Computer Science and Technology Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China School of Artificial Intelligence Anhui University Hefei China

ISBN: (纸本)9798350376548

In recent years, deep learning-based medical image registration algorithms have demonstrated notable achievements in improving registration accuracy and speed. However, these algorithms have not explored the potential benefits of utilizing different networks to generate distinct deformation fields, which can then be integrated to produce a final deformation field. In this paper, we propose deformation field component attention fusion for coarse-to-fine medical image registration. Specifically, the registration process is divided into multiple stages, which generate different deformation fields that focus on capturing deformations of varying degrees. To ensure the effective integration of multiple deformation fields, we propose the Deformation Field Component Attention Fusion Module. This module separates the deformation field into three axial displacement components and performs independent attention fusion for the different axial displacement components. Through comparative experiments and ablation studies, we demonstrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

ϵ-π: A Nonparametric Model for Neural Power Spectra Decomposition

引用

IEEE Journal of Biomedical and Health Informatics 2024年第5期28卷 2624-2635页

作者： Hu, Shiang Zhang, Zhihao Zhang, Xiaochu Wu, Xiaopei Valdes-Sosa, Pedro A. Anhui University Anhui Provincial Key Lab of Multimodal Cognitive Computation Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China University of Science and Technology of China School of Humanities and Social Science Department of Psychology Hefei230026 China University of Electronic Science and Technology of China MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China

The power spectra estimated from the brain recordings are the mixed representation of aperiodic transient activity and periodic oscillations, i.e., aperiodic component (AC) and periodic component (PC). Quantitative neurophysiology requires precise decomposition preceding parameterizing each component. However, the shape, statistical distribution, scale, and mixing mechanism of AC and PCs are unclear, challenging the effectiveness of current popular parametric models such as FOOOF, IRASA, BOSC, etc. Here, was proposed to decompose the neural spectra by embedding the nonparametric spectra estimation with penalized Whittle likelihood and the shape language modeling into the expectation maximization framework. was validated on the synthesized spectra with loss statistics and on the sleep EEG and the large sample iEEG with evaluation metrics and neurophysiological evidence. Compared to FOOOF, both the simulation presenting shape irregularities and the batch simulation with multiple isolated peaks indicated that improved the fit of AC and PCs with less loss and higher F1-score in recognizing the centering frequencies and the number of peaks;the sleep EEG revealed that produced more distinguishable AC exponents and improved the sleep state classification accuracy;the iEEG showed that approached the clinical findings in peak discovery. Overall, offered good performance in the spectra decomposition, which allows flexible parameterization using descriptive statistics or kernel functions. is a seminal tool for brain signal decoding in fields such as cognitive neuroscience, brain-computer interface, neurofeedback, and brain diseases. © 2013 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：