检索结果-内蒙古大学图书馆

Adaptive multi-modal feature fusion for far and hard object detection

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2021年第2期12卷 232-241页

作者： LI Yang GE Hongwei Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi 214122 China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China

In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image ***,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection ***,semantema of each image feature map is enhanced by semantic information from all subsequent feature ***,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of ***,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target *** experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,*** the AP by 8.78%and 5.49%on medium and hard difficulty ***,our method achieves greater detection performance compared with many mainstream multi-modal methods,*** the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.

关键词： 3D object detection adaptive fusion multi-modal data fusion attention mechanism multi-neighborhood features

A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Jianjun Wu, Zebin Xiao, Liang Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China School of Computer Science Nanjing University of Science and Technology Nanjing China

Fusion-based hyperspectral image (HSI) superresolution aims to produce a high-spatial-resolution HSI by fusing a low-spatial-resolution HSI and a high-spatial-resolution multispectral image. Such a HSI super-resolution process can be modeled as an inverse problem, where the prior knowledge is essential for obtaining the desired solution. Motivated by the success of diffusion models, we propose a novel spectral diffusion prior for fusion-based HSI super-resolution. Specifically, we first investigate the spectrum generation problem and design a spectral diffusion model to model the spectral data distribution. Then, in the framework of maximum a posteriori, we keep the transition information between every two neighboring states during the reverse generative process, and thereby embed the knowledge of trained spectral diffusion model into the fusion problem in the form of a regularization term. At last, we treat each generation step of the final optimization problem as its subproblem, and employ the Adam to solve these subproblems in a reverse sequence. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach. The code of the proposed approach will be available on https://***/liuofficial/SDP. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse problems

Model inspired autoencoder for unsupervised hyperspectral image super-resolution

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jianjun Wu, Zebin Xiao, Liang Wu, Xiao-Jun The Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China The School of Computer Science Nanjing University of Science and Technology Nanjing China

This paper focuses on hyperspectral image (HSI) super-resolution that aims to fuse a low-spatial-resolution HSI and a high-spatial-resolution multispectral image to form a high-spatial-resolution HSI (HR-HSI). Existing deep learning-based approaches are mostly supervised that rely on a large number of labeled training samples, which is unrealistic. The commonly used model-based approaches are unsupervised and flexible but rely on hand-craft priors. Inspired by the specific properties of model, we make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner. This approach consists of an implicit autoencoder network built on the target HR-HSI that treats each pixel as an individual sample. The nonnegative matrix factorization (NMF) of the target HR-HSI is integrated into the autoencoder network, where the two NMF parts, spectral and spatial matrices, are treated as decoder parameters and hidden outputs respectively. In the encoding stage, we present a pixel-wise fusion model to estimate hidden outputs directly, and then reformulate and unfold the model’s algorithm to form the encoder network. With the specific architecture, the proposed network is similar to a manifold prior-based model, and can be trained patch by patch rather than the entire image. Moreover, we propose an additional unsupervised network to estimate the point spread function and spectral response function. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Spectroscopy

Collaborative representation-based robust face recognition by discriminative low-rank representation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhao, Wen Wu, Xiao-Jun Yin, He-Feng Li, Zi-Qi School of Internet of Things Engineering Jiangnan University Wuxi214122 China Jiangsu Provincial Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

We consider the problem of robust face recognition in which both the training and test samples might be corrupted because of disguise and occlusion. Performance of conventional subspace learning methods and recently proposed sparse representation based classification (SRC) might be degraded when corrupted training samples are provided. In addition, sparsity based approaches are time-consuming due to the sparsity constraint. To alleviate the aforementioned problems to some extent, in this paper, we propose a discriminative low-rank representation method for collaborative representation-based (DLRR-CR) robust face recognition. DLRR-CR not only obtains a clean dictionary, it further forces the sub-dictionaries for distinct classes to be as independent as possible by introducing a structural incoherence regularization term. Simultaneously, a low-rank projection matrix can be learned to remove the possible corruptions in the testing samples. Collaborative representation based classification (CRC) method is exploited in our proposed method which has closed-form solution. Experimental results obtained on public face databases verify the effectiveness and robustness of our method. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

No-reference image quality assessment based on dualchannel convolutional neural network

学校读者我要写书评

暂无评论

No-reference image quality assessment based on dualchannel c...

International Symposium in Sensing and Instrumentation in IoT Era (ISSI)

作者： Shuyu Huang Qingbing Sang Qin Wu Xiaojun Wu Chaofeng Li Jiangsu Provincial Engineerinig Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China Institutute of Logistics Science and Engineering Shanghai Maritime University Shanghai China

ISBN: (纸本)9781538656396

In recent years, convolutional neural networks have achieved more outstanding results and been widely used in the field of image quality assessment compared with the traditional handcraft method. This paper presents a no-reference image quality assessment method based on dual-channel convolutional neural network. The raw image is labeled by visual information fidelity and divided into multiple patches as input. After that, feature extraction is performed by two network channels with different pooling layers. The features are Iinearly stitched and sent to the fully connected layer. The experimental results on the LIVE database and the TID2008 database show that our model has the state-of-the-art performance and obtain a better consistency with human subjective assessment.

关键词： Image quality Feature extraction Convolutional neural networks Distortion Convolution Databases Visualization

Learning efficient structured dictionary for image classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Zi-Qi Sun, Jun Wu, Xiao-Jun Yin, He-Feng Jiangnan University School of Internet of Things Engineering Lihu Avenue Wuxi China Jiangsu Provincial Laboratory of Pattern Recognition and Computational Intelligence Lihu Avenue Wuxi China

Recent years have witnessed the success of dictionary learning (DL) based approaches in the domain of pattern classification. In this paper, we present an efficient structured dictionary learning (ESDL) method which takes both the diversity and label information of training samples into account. Specifically, ESDL introduces alternative training samples into the process of dictionary learning. To increase the discriminative capability of representation coefficients for classification, an ideal regularization term is incorporated into the objective function of ESDL. Moreover, in contrast with conventional DL approaches which impose computationally expensive `1-norm constraint on the coefficient matrix, ESDL employs `2-norm regularization term. Experimental results on benchmark databases (including four face databases and one scene dataset) demonstrate that ESDL outperforms previous DL approaches. More importantly, ESDL can be applied in a wide range of pattern classification tasks. The demo code of our proposed ESDL will be available at https://***/li-zi-qi/ESDL. Copyright © 2020, The Authors. All rights reserved.

关键词： Sampling

2DR1-PCA and 2DL1-PCA: Two variant 2DPCA algorithms based on none L2norm

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Xing Wu, Xiao-Jun Li, Zi-Qi Jiangnan University School of Internet of Things Engineering Lihu Avenue Wuxi China Jiangsu Provincial Laboratory of Pattern Recognition and Computational Intelligence Lihu Avenue Wuxi China

In this paper, two novel methods: 2DR1-PCA and 2DL1-PCA are proposed for face recognition. Compared to the traditional 2DPCA algorithm, 2DR1-PCA and 2DL1-PCA are based on the R1norm and L1norm, respectively. The advantage of these proposed methods is they are less sensitive to outliers. These proposed methods are tested on the ORL, YALE and XM2VTS databases and the performance of the related methods is compared experimentally. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

HTD-Mamba: Efficient Hyperspectral Target Detection with Pyramid State Space Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shen, Dunbin Zhu, Xuanbing Tian, Jiacheng Liu, Jianjun Du, Zhenrong Wang, Hongyu Ma, Xiaorui The School of Information and Communication Engineering DUT Artificial Intelligence Institute The Dalian Key Laboratory of Artificial Intelligence Dalian University of Technology Dalian116024 China The Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

Hyperspectral target detection (HTD) identifies objects of interest from complex backgrounds at the pixel level, playing a vital role in Earth observation. However, HTD faces challenges due to limited prior knowledge and spectral variations, leading to underfitting models and unreliable performance. To address these challenges, this paper proposes an efficient self-supervised HTD method with a pyramid state space model (SSM), named HTD-Mamba, which employs spectrally contrastive learning to distinguish between target and background based on the similarity measurement of intrinsic features. Specifically, to obtain sufficient training samples and leverage spatial contextual information, we propose a spatial-encoded spectral augmentation technique that encodes all surrounding pixels within a patch into a transformed view of the central pixel. Additionally, to explore global band correlations, we divide pixels into continuous group-wise spectral embeddings and introduce Mamba to HTD for the first time to model long-range dependencies of the spectral sequence with linear complexity. Furthermore, to alleviate spectral variation and enhance robust representation, we propose a pyramid SSM as a backbone to capture and fuse multiresolution spectral-wise intrinsic features. Extensive experiments conducted on four public datasets demonstrate that the proposed method outperforms state-of-the-art methods in both quantitative and qualitative evaluations. Code is available at https://***/shendb2022/HTD-Mamba. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

GPU-Based Efficient Parallel Heuristic Algorithm for High-Utility Itemset Mining in Large Transaction Datasets (Extended Abstract)

学校读者我要写书评

暂无评论

GPU-Based Efficient Parallel Heuristic Algorithm for High-Ut...

International Conference on Data engineering

作者： Wei Fang Haipeng Jiang Hengyang Lu Jun Sun Xiaojun Wu Jerry Chun-Wei Lin Department of Computer Science and Technology Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China Department of Distributed Systems and IT Devices Silesian University of Technology Poland

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Heuristic algorithms have been developed to find approximate solutions for high-utility itemset mining (HUIM) problems that compensate for the performance bottlenecks of exact algorithms. However, heuristic algorithms still face the problem of long runtime and insufficient mining quality, especially for large transaction datasets with thousands to tens of thousands of items and up to millions of transactions. To solve these problems, a novel GPU-based efficient parallel heuristic algorithm for HUIM (PHA-HUIM) is proposed in this paper. The iterative process of PHA-HUIM consists of three main steps: the search strategy, fitness evaluation, and ring topology communication. The search strategy and ring topology communication are designed to run in constant time on GPU. The parallelism of fitness evolution helps to substantially accelerate the algorithm. To improve the mining quality, a multi-start strategy with an unbalanced allocation strategy is employed in the search process. Ring topology communication is adopted to maintain population diversity. A load balancing strategy is introduced to reduce the thread divergence to improve the parallel efficiency. The experimental results on nine large datasets show that PHA-HUIM outperforms state-of-the-art HUIM algorithms in terms of speedup performance, runtime, and mining quality.

关键词： Runtime Itemsets Heuristic algorithms Sociology Approximation algorithms Search problems Topology