检索结果-内蒙古大学图书馆

3rd International Conference on Machine Learning, Cloud computing and Intelligent Mining, MLCCIM 2024

作者： Gao, Shuai Wu, Mengjiang Lv, Wanli Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230000 China

ISBN: (纸本)9789819624676

Deep Neural Networks (DNNs) have shown outstanding performance on a variety of tasks. However, their vulnerability to adversarial examples has become a significant concern in recent years. Of particular concern are imperceptible adversarial examples, which present a latent threat to safety-critical applications. In this work, we introduce an Attention-Gated Denoising Autoencoder model (AGDAE) designed to effectively detect imperceptible adversarial attacks. Our model utilizes innovative Attention-Gated Convolutional Blocks to enhance feature extraction and selection, thereby improving the model’s sensitivity to minute perturbations. By using an autoencoder model, our network is able to remove adversarial noise by reconstructing input images. Additionally, we combine a target-oriented detection framework to verify label consistency between reconstructed and original images, further enhancing adversarial example detection. Experiments on datasets such as CIFAR-10, and ImageNet validate the effectiveness of AGDAE in detecting imperceptible adversarial examples, maintaining a high detection accuracy even against highly sophisticated adversarial attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware coarse-to-fine alignment for text-image person retrieval

引用

Visual Intelligence 2025年第1期3卷 1-14页

作者： Deng, Yifei Chen, Zhengyu Li, Chenglong Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei 230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei 230601 China

Text-to-image person retrieval, a fine-grained cross-modal retrieval problem, aims to search for person images from an image library that match a given textual caption. Existing text-to-image person retrieval methods usually use fixed-point embedding to express the semantics of the two modalities and perform multi-granularity alignment between modalities in the embedding space. However, owing to the inherent mutual one-to-many correspondence between images and texts, it is often difficult for fixed-point embedding methods to adequately capture this relationship, leading to erroneous retrieval results. To address this problem, we propose a novel uncertainty-aware coarse-to-fine alignment method, which first maps fixed-point embedding to probability distributions and then aligns two modalities in terms of distributions and sampling points at a coarse-to-fine granularity, for accurate text-to-image person retrieval. Specifically, we first introduce two contrastive learning tasks of distribution contrast learning and point contrast learning, to achieve coarse-grained inter-modal alignment with uncertainty-aware. The distribution contrast learning task ensures that distributions with the same identity are as similar as possible across modalities through distribution-based contrastive learning. The point contrast learning task performs the contrastive learning of inter-modal and intra-modal sampling points, which not only models rich and diverse cross-modal associations, but also optimizes the learning of distributions. For the fine-grained association requirements of text-to-image person retrieval, we design the task of uncertainty-aware attribute masking language reconstruction, which achieves fine-grained alignment by randomly masking attribute words in the text and reconstructing them via inter-modal sample point interactions. Extensive experiments on two public datasets demonstrate the superior performance of our method. © The Author(s) 2025.

关键词： Coarse-to-fine alignment Contrastive learning Cross-modal retrieval Probalility distribution Uncertainty-aware

来源：评论

学校读者我要写书评

暂无评论

Efficient RGBT Tracking via Multi-Path Mamba Fusion Network

引用

IEEE Signal Processing Letters 2025年 32卷 1790-1794页

作者： Hong, Fanghua Wang, Wanyu Lu, Andong Liu, Lei Wang, Qunjing Anhui University School of Electronic Information Engineering Hefei230601 China Anhui University School of Artificial Intelligence Hefei230601 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Anhui University of Science and Technology School of Artificial Intelligence Hefei230601 China

RGBT tracking aims to fully exploit the complementary advantages of visible and infrared modalities to achieve robust tracking, thus the design of multimodal fusion network is crucial. However, existing methods typically adopt CNNs or Transformer networks to construct the fusion network, which poses a challenge in achieving a balance between performance and efficiency. To overcome this issue, we introduce an innovative visual state space (VSS) model, represented by Mamba, for RGBT tracking. In particular, we design a novel multi-path Mamba fusion network that achieves robust multimodal fusion capability while maintaining a linear overhead. First, we design a multi-path Mamba layer to sufficiently fuse two modalities in both global and local perspectives. Second, to alleviate the issue of inadequate VSS modeling in the channel dimension, we introduce a simple yet effective channel swapping layer. Extensive experiments conducted on four public RGBT tracking datasets demonstrate that our method surpasses existing state-of-the-art trackers. Notably, our fusion method achieves higher tracking performance compared to the well-known Transformer-based fusion approach (TBSI), while also achieving 92.8% and 80.5% reductions in parameter count and computational cost, respectively. © 1994-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Prototype Transferred Diverse Features for Day-night Cross-domain Facial Expression Recognition 16

Prototype Transferred Diverse Features for Day-night Cross-d...

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Ma, Teng Qi, Yuhan Wang, ZhuoRan Li, YiPei Wang, Jiaxiang State Grid Corporation of Shanxi Province Shanxi 030025 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Beijing Institute of Technology China Dublin International College Ireland

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

Facial Expression Recognition (FER) encounters significant challenges due to the limited sensitivity of visible light images in low light conditions. Most existing cross-domain emotion recognition studies have focused on domain adaptation for different visible light datasets, often neglecting the problem of emotion recognition under varying lighting conditions. To address this, we introduce the first cross-domain emotion recognition study for day and night environments, emphasizing the modal migration between normal visible light and low-light emotion maps. Considering the limited number of emotion maps and the reduced emotional detail in nighttime imaging, we designed an attention-switching diversified feature capture module to focus on facial expressions and extract more local emotional features that aid in migration. Given the significant domain shifts between samples in different lighting environments, we further developed a prototype feature transfer module to learn modality-independent category features and reduce domain differences between visible and low-light features. To tackle the challenge of numerous low sentiment value samples in the dataset, we introduce a high-confidence blending module to filter informative visible and infrared samples for fusion, producing features that combine the styles of both domains. Compared to state-of-the-art methods in domain adaptation and cross-domain emotion recognition, our approach demonstrates superior performance and validates its effectiveness. © 2025 SPIE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Camera-Proxy Enhanced Identity-Recalibration Learning for Unsupervised Visible-Infrared Person Re-Identification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Xia, Run-Sen Wang, Xue-Yan Chen, Si-Bao Tang, Jin Luo, Bin Anhui University Moe Key Laboratory of Icsp Imis Laboratory of Anhui Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Zenmorn-AHU Ai Joint Laboratory School of Computer Science and Technology Hefei230601 China

Visible-Infrared person Re-Identification (VI-ReID) involves querying images of the same person across visible and infrared modalities. To minimize annotation costs, Unsupervised Visible-Infrared person Re-Identification (UVI-ReID) using pseudo-label contrastive learning has emerged. Traditional UVI-ReID approaches often neglected camera domain information and relied on inadequate update strategies during training, only using cosine distance for testing, which led to incorrect mapping of cross-modal relationships. To address these issues, we propose Camera-proxy Enhanced Identity-recalibration Learning (CEIL). It consists of two main stages: first, it employs intramodal contrastive learning in conjunction with the camera-proxy, updates the memory bank using our innovative Difficulty-aware Cluster-based Memory Updating (DCMU) strategy, and applies Camera Domain-driven Local correlation (CDL) Loss to enhance the learning process. Then utilizes cross-modal contrastive learning, featuring our Proxy-enhanced Cross-modal Mapping (PCM) module, to recalibrate the identity relationships between different modalities. Graph network-based Camera constraint adjustment Re-ranking (GCR) method is adopted during test, utilizing camera domain information to recalibrate the correspondence between identities. Extensive experiments have demonstrated that CEIL achieving state-of-the-art performance on the SYSU-MM01, RegDB, and LLCM datasets and the GCR, as a general unsupervised re-ranking method, can further enhance performance of model on these datasets. The code will be released at https://***/maybeextra/CEIL. © 1991-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

CFENet: Contextual Feature Enhancement Network for Tiny Object Detection in Aerial Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Hu, Heng Chen, Si-Bao Tang, Jin Anhui University MOE Key Laboratory of ICSP Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Zenmorn-AHU AI Joint Laboratory School of Computer Science and Technology IMIS Laboratory of Anhui Province Hefei230601 China

With the development of deep learning techniques and object detectors, the performance of object detection has been rapidly improved. However, since tiny objects contain only a small number of pixels and lack appearance information, this creates difficulties for detector recognition. Although existing research has improved detection performance by fusing different feature layers to enhance feature information of objects, this also leads to the problem of mixed feature information, especially for tiny objects where features are easily covered, which exacerbates the difficulty of recognition. To solve the above problems, we propose a contextual feature enhancement network (CFENet), which is an efficient framework built on anchor-based object detectors. In CFENet, to effectively utilize contextual information around an object to enhance the detection of tiny objects, we use poolFormer to build a backbone to extract object features. To alleviate the feature blending problem caused by feature fusion, we propose a feature suppression module (FSM) that effectively suppresses background information and redundant features to enhance tiny object features. In addition, we utilize the improved Gaussian Wasserstein distance loss to modify the loss function to obtain high-quality bounding boxes, and we further manipulate the shallow feature layer of the output and then add a detection head to enhance the detection of tiny objects. We have conducted extensive experiments on the public datasets AI-TOD, VisDrone, and DOTA to demonstrate the effectiveness of our approach. © 1980-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DehazeMamba: SAR-guided Optical Remote Sensing Image Dehazing with Adaptive State Space Model

arXiv

引用

arXiv 2025年

作者： Zhao, Zhicheng Yan, Jinquan Li, Chenglong Wang, Xiao Tang, Jin Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province China

Optical remote sensing image dehazing presents significant challenges due to its extensive spatial scale and highly non-uniform haze distribution, which traditional single-image dehazing methods struggle to address effectively. While Synthetic Aperture Radar (SAR) imagery offers inherently haze-free reference information for large-scale scenes, existing SAR-guided dehazing approaches face two critical limitations: the integration of SAR information often diminishes the quality of haze-free regions, and the instability of feature quality further exacerbates cross-modal domain shift. To overcome these challenges, we introduce DehazeMamba, a novel SAR-guided dehazing network built on a progressive haze decoupling fusion strategy. Our approach incorporates two key innovations: a Haze Perception and Decoupling Module (HPDM) that dynamically identifies haze-affected regions through optical-SAR difference analysis, and a Progressive Fusion Module (PFM) that mitigates domain shift through a two-stage fusion process based on feature quality assessment. To facilitate research in this domain, we present MRSHaze, a large-scale benchmark dataset comprising 8,000 pairs of temporally synchronized, precisely geo-registered SAR-optical images with high resolution and diverse haze conditions. Extensive experiments demonstrate that DehazeMamba significantly outperforms state-of-the-art methods, achieving a 0.73 dB improvement in PSNR and substantial enhancements in downstream tasks such as semantic segmentation. The dataset is available at https://***/mmic-lcl/Datasets-and-benchmark-code. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

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

arXiv

引用

arXiv 2025年

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

In the realm of multi-object tracking, the challenge of accurately capturing the spatial and temporal relationships between objects in video sequences remains a significant hurdle. This is further complicated by frequent occurrences of mutual occlusions among objects, which can lead to tracking errors and reduced performance in existing methods. Motivated by these challenges, we propose a novel adaptive key frame mining strategy that addresses the limitations of current tracking approaches. Specifically, we introduce a key Frame Extraction (KFE) module that leverages reinforcement learning to adaptively segment videos, thereby guiding the tracker to exploit the intrinsic logic of the video content. This approach allows us to capture structured spatial relationships between different objects as well as the temporal relationships of objects across frames. To tackle the issue of object occlusions, we have developed an Intra-Frame Feature Fusion (IFF) module. Unlike traditional graph-based methods that primarily focus on inter-frame feature fusion, our IFF module uses a Graph Convolutional Network (GCN) to facilitate information exchange between the target and surrounding objects within a frame. This innovation significantly enhances target distinguishability and mitigates tracking loss and appearance similarity due to occlusions. By combining the strengths of both long and short trajectories and considering the spatial relationships between objects, our proposed tracker achieves impressive results on the MOT17 dataset, i.e., 68.6 HOTA, 81.0 IDF1, 66.6 AssA, and 893 IDS, proving its effectiveness and accuracy. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Enhancement Network for Low-quality Multi-spectral Vehicle Re-identification

arXiv

引用

arXiv 2025年

作者： Zheng, Aihua Sun, Yongqi Wang, Zi Li, Chenglong Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Biomedical Engineering Anhui Medical University Hefei230032 China

The performance of multi-spectral vehicle Re-identification (ReID) is significantly degraded when some important discriminative cues in visible, near infrared and thermal infrared spectra are lost. Existing methods generate or enhance missing details in low-quality spectra data using the high-quality one, generally called the primary spectrum, but how to justify the primary spectrum is a challenging problem. In addition, when the quality of the primary spectrum is low, the enhancement effect would be greatly degraded, thus limiting the performance of multi-spectral vehicle ReID. To address these problems, we propose the Collaborative Enhancement Network (CoEN), which generates a high-quality proxy from all spectra data and leverages it to supervise the selection of primary spectrum and enhance all spectra features in a collaborative manner, for robust multi-spectral vehicle ReID. First, to integrate the rich cues from all spectra data, we design the Proxy Generator (PG) to progressively aggregate multi-spectral features. Second, we design the Dynamic Quality Sort Module (DQSM), which sorts all spectra data by measuring their correlations with the proxy, to accurately select the primary spectra with the highest correlation. Finally, we design the Collaborative Enhancement Module (CEM) to effectively compensate for missing contents of all spectra by collaborating the primary spectra and the proxy, thereby mitigating the impact of low-quality primary spectra. Extensive experiments on three benchmark datasets are conducted to validate the efficacy of the proposed approach against other multi-spectral vehicle ReID methods. The codes will be released at https://***/yongqisun/CoEN. Copyright © 2025, The Authors. All rights reserved.

关键词： Near infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagation

引用

ACM Transactions on Multimedia computing, Communications and Applications 2025年第4期21卷

作者： Wang, Jiahui Xu, Qin Jiang, Bo Luo, Bin The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China The Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

The transductive Few-shot Learning (FSL) mostly employs either prototype learning or label propagation methods to generalize to new classes by using the information of all query samples. However, existing methods have several main limitations. First, the prototype methods mainly focus on support samples which fail to fully exploit the relationships of query samples. Second, existing label propagation methods are generally not effective for the class-imbalanced problem. Third, existing works usually optimize the learnable parameters during inference which significantly reduces the efficiency of existing methods. To address these limitations, this article proposes an efficient and robust method for transductive FSL problem, termed Prototype-based Soft-label Propagation (PSLP), which combines the prototype learning and label propagation together for FSL problem. In our proposed method, first, the soft-label presentation for each query sample is estimated by leveraging prototypes. Then, the soft-label propagation is conducted on the learned query-support graph and the prototype representation is rectified. Both steps are conducted progressively for boosting the performance. Moreover, to learn effective prototypes for soft-label estimation and the desirable query-support graph for soft-label propagation, we design a new joint message passing scheme to learn the sample presentation and relational graph jointly. The PSLP method is parameter-free and can be implemented very efficiently. The experiments conducted on four popular benchmarks show that our method achieves competitive results on both balanced and imbalanced settings compared to the state-of-the-art methods. The code is released at https://***/mobulan/PSLP. © 2025 Copyright held by the owner/author(s).

关键词： Few-shot learning Transductive learning Message passing Label propagation

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：