检索结果-内蒙古大学图书馆

General and robust voxel feature learning with Transformer for 3D object detection

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2022年第1期13卷 51-60页

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

The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object *** by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional *** first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud *** we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the ***,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object *** voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature *** results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.

关键词： 3D object detection self-attention networks voxel feature with Transformer(VFT) point cloud encoder-decoder

Hierarchical Knowledge Transfer Network for Distantly Supervised Relation Extraction

学校读者我要写书评

暂无评论

Hierarchical Knowledge Transfer Network for Distantly Superv...

International Joint Conference on Neural Networks (IJCNN)

作者： Wei Song Weishuai Gu School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China

Distantly supervised relation extraction (DSRE) aims to identify the relation between the two entities (e.g. name and location). Most existing methods extract semantic features from each level separately, without taking into account the transfer of hierarchical knowledge obtained at various levels. As a result, a large amount of knowledge that can improve the quality of the feature representations is lost, resulting in decreased performance for predicting entity relations. In this paper, we propose a novel framework termed the Hierarchical Knowledge Transfer Network (HKTN) that is capable of transferring hierarchical knowledge learned from different levels to improve the performance of predicting entity relations. Specifically, the two representation refinement blocks with re-calibrators at the bag and group levels construct robust bag features and comprehensive group features, respectively. During the construction process, the high-level features are capable of guiding the learning of the bottom-level features using the two re-calibrators. As the construction of the high-level feature representations is based on the bottom-level feature representations, prediction-based contrastive learning fully excavates bottom-level features, which can improve the quality of the feature representation at each level. The experimental results demonstrate that our proposed HKTN achieves an obvious improvement on the two benchmark datasets, including NYT-10 and GDS.

关键词：

Lace Fabric Image Retrieval Using Siamese Neural Network

学校读者我要写书评

暂无评论

Lace Fabric Image Retrieval Using Siamese Neural Network

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： DongDong Xu Yueyang Li HaiChi Luo Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China College of Internet of Things Engineering Jiangnan University Wuxi China

ISBN: (纸本)9781665446006

An efficient lace fabric image retrieval method based on DCNN learning features is proposed in this paper. Fine-tuning with Siamese Neural Network is used to learn effective feature of lace fabric image. During the process of training the Siamese Neural Network, hard negative pairs are selective to achieve fast convergence and good performance. The DCNN learning features are combined with the unique shape feature to enable accurate and efficient retrieval of massive image data. Experimental results demonstrate the effectiveness of retrieval performance of the proposed algorithm and possible practical application of the retrieval system in lace fabric industry to improve management efficiency.

关键词： Training Industries Shape Image processing Conferences Neural networks Image retrieval

Cross-modal subspace learning via Kernel correlation maximization and discriminative structure preserving

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yu, Jun Wu, Xiao-Jun School of IoT Engineering Jiangnan University Wuxi214122 China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition Computational Intelligence Jiangnan University Wuxi214122 China

The measure between heterogeneous data is still an open problem. Many research works have been developed to learn a common subspace where the similarity between different modalities can be calculated directly. However, most of existing works focus on learning a latent subspace but the semantically structural information is not well preserved. Thus, these approaches cannot get desired results. In this paper, we propose a novel framework, termed Cross-modal subspace learning via Kernel correlation maximization and Discriminative structure-preserving (CKD), to solve this problem in two aspects. Firstly, we construct a shared semantic graph to make each modality data preserve the neighbor relationship semantically. Secondly, we introduce the Hilbert-Schmidt Independence Criteria (HSIC) to ensure the consistency between feature-similarity and semantic-similarity of samples. Our model not only considers the inter-modality correlation by maximizing the kernel correlation but also preserves the semantically structural information within each modality. The extensive experiments are performed to evaluate the proposed framework on the three public datasets. The experimental results demonstrated that the proposed CKD is competitive compared with the classic subspace learning methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Unsupervised concatenation hashing via combining subspace learning and graph embedding for cross-Modal image retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yu, Jun Wu, Xiao-Jun School of IoT Engineering Jiangnan University Wuxi214122 China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

Different from the content-based image retrieval methods, cross-modal image retrieval methods uncover the rich semantic-level information of social images to further understand image contents. As multiple modal data depict a common object from multiple perspectives, many works focus on learning the unified subspace representation. Recently, hash representation has received much attention in the retrieval field. In common Hamming space, how to directly preserve the local manifold structure among objects become an interesting problem. Most of the unsupervised hashing methods attempt to solve it by constructing a neighborhood graph on every modality respectively. However, it is hard to decide the weight factor of each graph to get the optimal graph. To overcome this problem, we adopt the concatenated features to represent the common object since the information implied by different modalities is complementary. In our framework, Locally Linear Embedding and Locality Preserving Projection are introduced to reconstruct the manifold structure of the original space. Besides, The 2,1-norm constraint is imposed on the projection matrices to explore the discriminative hashing functions. Extensive experiments are performed on three public datasets and the experimental results show that our method outperforms several classic unsupervised hashing models. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Dual-Branch Reconstruction Network for Industrial Anomaly Detection with RGB-D Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bi, Chenyang Li, Yueyang Luo, Haichi Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China College of Internet of Things Engineering Jiangnan University 1800 Lihu Avenue Jiangsu Wuxi China

Unsupervised anomaly detection methods are at the forefront of industrial anomaly detection efforts and have made notable progress. Previous work primarily used 2D information as input, but multi-modal industrial anomaly detection based on 3D point clouds and RGB images is just beginning to emerge. The regular approach involves utilizing large pre-trained models for feature representation and storing them in memory banks. However, the above methods require a longer inference time and higher memory usage, which cannot meet the real-time requirements of the industry. To overcome these issues, we propose a lightweight dual-branch reconstruction network(DBRN) based on RGB-D input, learning the decision boundary between normal and abnormal examples. The requirement for alignment between the two modalities is eliminated by using depth maps instead of point cloud input. Furthermore, we introduce an importance scoring module in the discriminative network to assist in fusing features from these two modalities, thereby obtaining a comprehensive discriminative result. DBRN achieves 92.8% AUROC with high inference efficiency on the MVTec 3D-AD dataset without large pre-trained models and memory banks. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Real-time instance segmentation based on contour learning

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2024年第3期15卷 328-337页

作者： GE Rui LIU Dengfeng ZHOU Haojie CHAI Zhilei WU Qin School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory Pattern Recognition and Computational Intelligence Jiangnan UniversityWuxi 214122China

Instance segmentation plays an important role in image *** Deep Snake algorithm based on contour iteration deforms an initial bounding box to an instance contour end-to-end,which can improve the performance of instance segmentation,but has defects such as slow segmentation speed and sub-optimal initial *** solve these problems,a real-time instance segmentation algorithm based on contour learning was ***,ShuffleNet V2 was used as backbone network,and the receptive field of the model was expanded by using a 5×5 convolution ***,a lightweight up-sampling module,multi-stage aggregation(MSA),performs residual fusion of multi-layer features,which not only improves segmentation speed,but also extracts effective features more ***,a contour initialization method for network learning was designed,and a global contour feature aggregation mechanism was used to return a coarse contour,which solves the problem of excessive error between manually initialized contour and real ***,the Snake deformation module was used to iteratively optimize the coarse contour to obtain the final instance *** experimental results showed that the proposed method improved the instance segmentation accuracy on semantic boundaries dataset(SBD),Cityscapes and Kins datasets,and the average precision reached 55.8 on the SBD;Compared with Deep Snake,the model parameters were reduced by 87.2%,calculation amount was reduced by 78.3%,and segmentation speed reached 39.8 frame·s−1 when instance segmentation was performed on an image with a size of 512×512 pixels on a 2080Ti *** proposed method can reduce resource consumption,realize instance segmentation tasks quickly and accurately,and therefore is more suitable for embedded platforms with limited resources.

关键词： instance segmentation ShuffleNet V2 lightweight network contour initialization

A multi-view K-multiple-means clustering method

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2021年第4期12卷 405-411页

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

The K-multiple-means(KMM)retains the simple and efficient advantages of the K-means algorithm by setting multiple subclasses,and improves its effect on non-convex data *** aiming at the problem that it cannot be applied to the Internet on a multi-view data set,a multi-view K-multiple-means(MKMM)clustering method is proposed in this *** new algorithm introduces view weight parameter,reserves the design of setting multiple subclasses,makes the number of clusters as constraint and obtains clusters by solving optimization *** new algorithm is compared with some popular multi-view clustering *** effectiveness of the new algorithm is proved through the analysis of the experimental results.

关键词： K-multiple-means(KMM)clustering weight parameters multi-view K-multiple-means(MKMM)method

Multiplication fusion of sparse and collaborative-competitive representation 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 School of Internet of Things Engineering Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

Representation based classification methods have become a hot research topic during the past few years, and the two most prominent approaches are sparse representation based classification (SRC) and collaborative representation based classification (CRC). CRC reveals that it is the collaborative representation rather than the sparsity that makes SRC successful. Nevertheless, the dense representation of CRC may not be discriminative which will degrade its performance for classification tasks. To alleviate this problem to some extent, we propose a new method called sparse and collaborative-competitive representation based classification (SCCRC) for image classification. Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively. Then the fused coefficient is derived by multiplying the coefficients of SRC and CCRC. Finally, the test sample is designated to the class that has the minimum residual. Experimental results on several benchmark databases demonstrate the efficacy of our proposed SCCRC. The source code of SCCRC is accessible at https://***/li-zi-qi/SCCRC. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification