Query：
学者姓名：翁谦
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
提出一种多层次自适应知识蒸馏方法,以提升轻量化模型的性能.首先,针对遥感影像类别间差异程度不均衡的问题,通过改进输出层知识蒸馏中的温度机制,提出一种自适应温度机制,促进学生模型更好地学习大且深的教师模型输出层概率分布知识;然后,通过添加辅助卷积块来融入特征层的知识蒸馏方法,使学生模型学习教师模型的多层次知识;最后,在UCM、AID和NWPU这 3 个公开数据集上进行实验.结果表明:所提方法蒸馏后的学生模型参数量仅为教师模型的 6%,其分类精度较蒸馏前最多可提升 7.78%,比其他网络模型更便于部署在末端.
Keyword ：
卷积神经网络 卷积神经网络 场景分类 场景分类 特征蒸馏 特征蒸馏 知识蒸馏 知识蒸馏 自适应温度蒸馏 自适应温度蒸馏
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 翁谦 , 黄志铭 , 林嘉雯 et al. 多层次自适应知识蒸馏的轻量化高分遥感场景分类 [J]. | 福州大学学报（自然科学版） , 2023 , 51 (4) : 459-466 . |
| MLA | 翁谦 et al. "多层次自适应知识蒸馏的轻量化高分遥感场景分类" . | 福州大学学报（自然科学版） 51 . 4 (2023) : 459-466 . |
| APA | 翁谦 , 黄志铭 , 林嘉雯 , 简彩仁 , 廖祥文 . 多层次自适应知识蒸馏的轻量化高分遥感场景分类 . | 福州大学学报（自然科学版） , 2023 , 51 (4) , 459-466 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Models based on convolutional neural networks (CNNs) have achieved remarkable advances in high-resolution remote sensing (HRRS) images scene classification, but there are still challenges due to the high similarity among different categories and loss of local information. To address this issue, a multigranularity alternating feature mining (MGA-FM) framework is proposed in this article to learn and fuse both global and local information for HRRS scene classification. First, a region confusion mechanism is adopted to guide network's shallow layers to adaptively learn the salient features of distinguishing regions. Second, an alternating comprehensive training strategy is designed to capture and fuse shallow local feature information and deep semantic information to enhance feature representation capabilities. In particular, the MGA-FM framework can be flexibly embedded in various CNN backbone networks as a training mechanism. Extensive experimental results and visualization analysis on three remote sensing scene datasets indicated that the proposed method can achieve competitive classification performance.
Keyword ：
Convolutional neural network (CNN) Convolutional neural network (CNN) feature mining feature mining local detailed information local detailed information remote sensing image remote sensing image scene classification scene classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Weng, Qian , Huang, Zhiming , Lin, Jiawen et al. Remote Sensing Scene Classification Via Multigranularity Alternating Feature Mining [J]. | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING , 2023 , 16 : 318-330 . |
| MLA | Weng, Qian et al. "Remote Sensing Scene Classification Via Multigranularity Alternating Feature Mining" . | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 16 (2023) : 318-330 . |
| APA | Weng, Qian , Huang, Zhiming , Lin, Jiawen , Jian, Cairen , Mao, Zhengyuan . Remote Sensing Scene Classification Via Multigranularity Alternating Feature Mining . | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING , 2023 , 16 , 318-330 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Accurate building extraction for high-resolution remote sensing images is critical for topographic mapping, urban planning, and many other applications. Its main task is to label each pixel point as a building or non-building. Although deep-learning-based algorithms have significantly enhanced the accuracy of building extraction, fully automated methods for building extraction are limited by the requirement for a large number of annotated samples, resulting in a limited generalization ability, easy misclassification in complex remote sensing images, and higher costs due to the need for a large number of annotated samples. To address these challenges, this paper proposes an improved interactive building extraction model, ARE-Net, which adopts a deep interactive segmentation approach. In this paper, we present several key contributions. Firstly, an adaptive-radius encoding (ARE) module was designed to optimize the interaction features of clicks based on the varying shapes and distributions of buildings to provide maximum a priori information for building extraction. Secondly, a two-stage training strategy was proposed to enhance the convergence speed and efficiency of the segmentation process. Finally, some comprehensive experiments using two models of different sizes (HRNet18s+OCR and HRNet32+OCR) were conducted on the Inria and WHU building datasets. The results showed significant improvements over the current state-of-the-art method in terms of NoC90. The proposed method achieved performance enhancements of 7.98% and 13.03% with HRNet18s+OCR and 7.34% and 15.49% with HRNet32+OCR on the WHU and Inria datasets, respectively. Furthermore, the experiments demonstrated that the proposed ARE-Net method significantly reduced the annotation costs while improving the convergence speed and generalization performance.
Keyword ：
adaptive-radius encoding adaptive-radius encoding interactive building extraction interactive building extraction remote sensing remote sensing two-stage training two-stage training
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Weng, Qian , Wang, Qin , Lin, Yifeng et al. ARE-Net: An Improved Interactive Model for Accurate Building Extraction in High-Resolution Remote Sensing Imagery [J]. | REMOTE SENSING , 2023 , 15 (18) . |
| MLA | Weng, Qian et al. "ARE-Net: An Improved Interactive Model for Accurate Building Extraction in High-Resolution Remote Sensing Imagery" . | REMOTE SENSING 15 . 18 (2023) . |
| APA | Weng, Qian , Wang, Qin , Lin, Yifeng , Lin, Jiawen . ARE-Net: An Improved Interactive Model for Accurate Building Extraction in High-Resolution Remote Sensing Imagery . | REMOTE SENSING , 2023 , 15 (18) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Hyperspectral images can provide dozens to hundreds of continuous spectral bands, greatly enhancing the richness of information. However, the redundancy among adjacent bands leads to increased data processing complexity. Despite the recent introduction of numerous band selection methods, there has been limited focus on incorporating context information from the entire spectral range into this task. Furthermore, researchers have primarily concentrated on band informativeness and sparse representation for reconstructing all bands, often overlooking the separability of classes in downstream tasks. To address these challenges, we propose a hyperspectral band selection network combining Siamese Network Local-Global Attention (SLGA). This approach first segments the hyperspectral image into homogeneous regions and constructs sample pairs based on a random elimination strategy. Next, it utilizes the Local-Global Attention (L-GA) mechanism to obtain band weights that capture both local and global spectral structures. These reweighted bands are then fed into a twin network to obtain their high-dimensional representations, compute loss values, and update network parameters. Finally, extensive classification experiments using SVM, KNN, and LDA classifiers are conducted on the Indian Pines and Botswana hyperspectral image datasets. The results from these experiments on benchmark datasets demonstrate that the proposed SLGA method performs exceptionally well, outperforming state-of-the-art algorithms. © 2023 IEEE.
Keyword ：
Classification (of information) Classification (of information) Convolutional neural networks Convolutional neural networks Data handling Data handling Image enhancement Image enhancement Support vector machines Support vector machines
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | An, Yuan , Chen, Guangjian , Huang, Dehua et al. A Hyperspectral Band Selection Network Combining Siamese Network and Local-Global Attention [C] . 2023 : 705-710 . |
| MLA | An, Yuan et al. "A Hyperspectral Band Selection Network Combining Siamese Network and Local-Global Attention" . (2023) : 705-710 . |
| APA | An, Yuan , Chen, Guangjian , Huang, Dehua , Zheng, Huiqin , Wang, Qin , Jian, Cairen et al. A Hyperspectral Band Selection Network Combining Siamese Network and Local-Global Attention . (2023) : 705-710 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Semantic segmentation in high-resolution aerial images is a fundamental and challenging task with a wide range of applications. Although many segmentation methods with convolutional neural networks have achieved inspiring results, it is still difficult to distinguish regions with similar spectral features only using high-resolution data. Besides, the traditional data-independent upsampling methods may lead to suboptimal results. This letter proposes a multisensor data fusion model (MSDFM). Following the classical encoder-decoder structure, MSDFM regards colored digital surface models (colored-DSMs) data as a complementary input for further detailed feature extraction. A data-dependent upsampling (DUpsampling) method is adopted in the decoder stage instead of the common upsampling approaches to improve the classification accuracy of pixels of the small objects. Extensive experiments on Vaihingen and Potsdam datasets demonstrate that our proposed MSDFM outperforms most related models. Significantly, segmentation performance for the car category surpasses state-of-the-art methods over the International Society of Photogrammetry and Remote Sensing (ISPRS) Vaihingen dataset.
Keyword ：
Automobiles Automobiles Decoding Decoding Deconvolution Deconvolution Digital surface model (DSM) Digital surface model (DSM) Feature extraction Feature extraction high-resolution aerial images high-resolution aerial images Image segmentation Image segmentation Semantics Semantics semantic segmentation semantic segmentation Vegetation Vegetation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Weng, Qian , Chen, Hao , Chen, Hongli et al. A Multisensor Data Fusion Model for Semantic Segmentation in Aerial Images [J]. | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS , 2022 , 19 . |
| MLA | Weng, Qian et al. "A Multisensor Data Fusion Model for Semantic Segmentation in Aerial Images" . | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 19 (2022) . |
| APA | Weng, Qian , Chen, Hao , Chen, Hongli , Guo, Wenzhong , Mao, Zhengyuan . A Multisensor Data Fusion Model for Semantic Segmentation in Aerial Images . | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS , 2022 , 19 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对最小二乘回归子空间聚类法在求解表示系数时忽略了样本相似度的不足，提出改进方法。基于样本相互重构的表示系数矩阵和样本相似度矩阵有很大的关联定义系数增强项，求解可以保持样本相似度的表示系数矩阵，提出系数增强最小二乘回归子空间聚类法。在8个标准数据集上的实验表明该方法可以提高最小二乘回归子空间聚类法的聚类性能。
Keyword ：
子空间聚类 子空间聚类 最小二乘回归 最小二乘回归 系数增强 系数增强 高维数据 高维数据
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 简彩仁 , 翁谦 , 夏靖波 . 系数增强最小二乘回归子空间聚类法 [J]. | 计算机工程与应用 , 2022 , 58 (20) : 73-78 . |
| MLA | 简彩仁 et al. "系数增强最小二乘回归子空间聚类法" . | 计算机工程与应用 58 . 20 (2022) : 73-78 . |
| APA | 简彩仁 , 翁谦 , 夏靖波 . 系数增强最小二乘回归子空间聚类法 . | 计算机工程与应用 , 2022 , 58 (20) , 73-78 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
借鉴基于正则回归的无监督并行正交基聚类特征选择法和最大互信息系数,提出正交基低冗余无监督特征选择法.该方法在正交基下选择具有判别能力的特征,可用最大互信息系数矩阵选择低冗余性的特征子集. 4个图像数据集上的实验结果表明:该方法选择的特征子集可以提高聚类准确率.
Keyword ：
低冗余 低冗余 无监督 无监督 正交基 正交基 特征选择 特征选择 聚类 聚类
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 简彩仁 , 翁谦 . 正交基低冗余无监督特征选择法 [J]. | 福州大学学报(自然科学版) , 2022 , 50 (01) : 1-8 . |
| MLA | 简彩仁 et al. "正交基低冗余无监督特征选择法" . | 福州大学学报(自然科学版) 50 . 01 (2022) : 1-8 . |
| APA | 简彩仁 , 翁谦 . 正交基低冗余无监督特征选择法 . | 福州大学学报(自然科学版) , 2022 , 50 (01) , 1-8 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对最小二乘回归子空间聚类法没有考虑近邻样本对求解表示系数的影响这一不足，提出近邻系数协同强化子空间聚类法.该方法利用近邻样本相似导致表示系数接近的思想定义近邻系数协同强化项.通过近邻样本的系数强化表示系数，从而得到更能反映样本相似度的相似矩阵，进而提高聚类准确率.在6个人脸图像数据集上的实验表明，该方法是有效的.
Keyword ：
人脸图像 人脸图像 协同强化 协同强化 子空间聚类 子空间聚类 近邻系数 近邻系数
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 许毅强 , 夏靖波 , 简彩仁 et al. 近邻系数协同强化人脸图像子空间聚类法 [J]. | 福州大学学报(自然科学版) , 2022 , 50 (05) : 581-586 . |
| MLA | 许毅强 et al. "近邻系数协同强化人脸图像子空间聚类法" . | 福州大学学报(自然科学版) 50 . 05 (2022) : 581-586 . |
| APA | 许毅强 , 夏靖波 , 简彩仁 , 翁谦 . 近邻系数协同强化人脸图像子空间聚类法 . | 福州大学学报(自然科学版) , 2022 , 50 (05) , 581-586 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Hyperspectral Images(HSIs) are data containing abundant spatial and spectral information, which is collected by advanced remote sensors. HSI Classification is a pixel-wise classification task that has broad prospects in the era of science and technology. In recent years, the widely used convolutional neural networks (CNNs) have come to the leading place in HSI Classification. However, the lack of utilization of spatial information limits its further application. To solve this issue, we considered the recently proposed Vision Transformer(ViT), which is modularized structures that are entirely based on self-attention mechanism. Furthermore, we proposed a patch-wise radially-accumulate module for ViT(RA-ViT) in HSI Classification. We evaluated the proposed method on Indian Pines(IP) and Kennedy Space Center(KSC) datasets. The results of experiments demonstrate the effectiveness of RA-ViT with comparison to current advanced models. © Published under licence by IOP Publishing Ltd.
Keyword ：
Image classification Image classification Neural networks Neural networks Remote sensing Remote sensing Space platforms Space platforms Spectroscopy Spectroscopy
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Yuyang , Weng, Qian , Lin, Jiawen et al. RA-ViT:Patch-wise Radially-Accumulate Module for ViT in Hyperspectral Image Classification [C] . 2022 . |
| MLA | Wu, Yuyang et al. "RA-ViT:Patch-wise Radially-Accumulate Module for ViT in Hyperspectral Image Classification" . (2022) . |
| APA | Wu, Yuyang , Weng, Qian , Lin, Jiawen , Jian, Cairen . RA-ViT:Patch-wise Radially-Accumulate Module for ViT in Hyperspectral Image Classification . (2022) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Current mainstream deep learning network models have many problems such as inner cavity, discontinuity, missed periphery, and irregular boundaries when applied to building extraction from high spatial resolution remote sensing images. This paper proposed the RMAU-Net model by designing a new activation function (Activate Customized or Not, ACON) and integrating residuals block with channel-space and criss-cross attention module based on the U-Net model structure. The ACON activation function in the model allows each neuron to be activated or not activated adaptively, which helps improve the generalization ability and transmission performance of the model. The residual module is used to broaden the depth of the network, reduce the difficulty in training and learning, and obtain deep semantic feature information. The channel-spatial attention module is used to enhance the correlation between encoding and decoding information, suppress the influence of irrelevant background region, and improve the sensitivity of the model. The cross attention module aggregates the context information of all pixels on the cross path and captures the global context information by circular operation to improve the global correlation between pixels. The building extraction experiment using the Massachusetts dataset as samples shows that among all the 7 comparison models, the proposed RMA-UNET model is optimal in terms of intersection of union and F1-score, as well as indexes of precision and recall, and the overall performance of RMAU-Net is better than similar models. Each module is added step by step to further verify the validity of each module and the reliability of the proposed method. ©2022, Science Press. All right reserved.
Keyword ：
Chemical activation Chemical activation Convolutional neural networks Convolutional neural networks Deep learning Deep learning Extraction Extraction Pixels Pixels Remote sensing Remote sensing Semantics Semantics Space optics Space optics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Xinhui , Mao, Zhengyuan , Weng, Qian et al. A Neural Network based on Residual Multi-attention and ACON Activation Function for Extract Buildings [J]. | Journal of Geo-Information Science , 2022 , 24 (4) : 792-801 . |
| MLA | Wu, Xinhui et al. "A Neural Network based on Residual Multi-attention and ACON Activation Function for Extract Buildings" . | Journal of Geo-Information Science 24 . 4 (2022) : 792-801 . |
| APA | Wu, Xinhui , Mao, Zhengyuan , Weng, Qian , Shi, Wenzao . A Neural Network based on Residual Multi-attention and ACON Activation Function for Extract Buildings . | Journal of Geo-Information Science , 2022 , 24 (4) , 792-801 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
