Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to est...Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.展开更多
针对多目标识别过程中点云分类和分割精度不高的问题,提出了一种基于改进Transformer模型的点云分类与分割方法DRPT(Double randomness Point Transformer),该方法在Transformer模型卷积投影层创建新的点嵌入,利用局部邻域的动态处理在...针对多目标识别过程中点云分类和分割精度不高的问题,提出了一种基于改进Transformer模型的点云分类与分割方法DRPT(Double randomness Point Transformer),该方法在Transformer模型卷积投影层创建新的点嵌入,利用局部邻域的动态处理在数据特征向量中持续增加全局特征属性,从而提高多目标识别中点云分类和分割的精度。实验中采用了标准基准数据集(ModelNet40、ShapeNet部分分割和SemanticKITTI场景语义分割数据集)以验证模型的性能,实验结果表明:DRPT模型的pIoU值为85.9%,比其他模型平均高出3.5%,有效提高了多目标识别检测时点云分类与分割精度,是对智能网联技术发展的有效支撑。展开更多
针对多变量时序(Multivariate Time Series,MTS)分类中长序列数据难以捕捉时序特征的问题,提出一种基于双向稀疏Transformer的时序分类模型BST(Bidirectional Sparse Transformer),提高了MTS分类任务的准确度.BST模型使用Transformer框...针对多变量时序(Multivariate Time Series,MTS)分类中长序列数据难以捕捉时序特征的问题,提出一种基于双向稀疏Transformer的时序分类模型BST(Bidirectional Sparse Transformer),提高了MTS分类任务的准确度.BST模型使用Transformer框架,构建了一种基于活跃度得分的双向稀疏注意力机制.基于KL散度构建活跃度评价函数,并将评价函数的非对称问题转变为对称权重问题.据此,对原有查询矩阵、键值矩阵进行双向稀疏化,从而降低原Transformer模型中自注意力机制运算的时间复杂度.实验结果显示,BST模型在9个长序列数据集上取得最高平均排名,在临界差异图中领先第2名35.7%,对于具有强时序性的乙醇浓度数据集(Ethanol Concentration,EC),分类准确率提高30.9%.展开更多
针对主流Transformer网络仅对输入像素块做自注意力计算而忽略了不同像素块间的信息交互,以及输入尺度单一导致局部特征细节模糊的问题,本文提出一种基于Transformer并用于处理视觉任务的主干网络ConvFormer. ConvFormer通过所设计的多...针对主流Transformer网络仅对输入像素块做自注意力计算而忽略了不同像素块间的信息交互,以及输入尺度单一导致局部特征细节模糊的问题,本文提出一种基于Transformer并用于处理视觉任务的主干网络ConvFormer. ConvFormer通过所设计的多尺度混洗自注意力模块(Channel-Shuffle and Multi-Scale attention,CSMS)和动态相对位置编码模块(Dynamic Relative Position Coding,DRPC)来聚合多尺度像素块间的语义信息,并在前馈网络中引入深度卷积提高网络的局部建模能力.在公开数据集ImageNet-1K,COCO 2017和ADE20K上分别进行图像分类、目标检测和语义分割实验,ConvFormer-Tiny与不同视觉任务中同量级最优网络RetNetY-4G,Swin-Tiny和ResNet50对比,精度分别提高0.3%,1.4%和0.5%.展开更多
基金supported in part by the Nationa Natural Science Foundation of China (61876011)the National Key Research and Development Program of China (2022YFB4703700)+1 种基金the Key Research and Development Program 2020 of Guangzhou (202007050002)the Key-Area Research and Development Program of Guangdong Province (2020B090921003)。
文摘Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.
文摘针对多目标识别过程中点云分类和分割精度不高的问题,提出了一种基于改进Transformer模型的点云分类与分割方法DRPT(Double randomness Point Transformer),该方法在Transformer模型卷积投影层创建新的点嵌入,利用局部邻域的动态处理在数据特征向量中持续增加全局特征属性,从而提高多目标识别中点云分类和分割的精度。实验中采用了标准基准数据集(ModelNet40、ShapeNet部分分割和SemanticKITTI场景语义分割数据集)以验证模型的性能,实验结果表明:DRPT模型的pIoU值为85.9%,比其他模型平均高出3.5%,有效提高了多目标识别检测时点云分类与分割精度,是对智能网联技术发展的有效支撑。
文摘针对主流Transformer网络仅对输入像素块做自注意力计算而忽略了不同像素块间的信息交互,以及输入尺度单一导致局部特征细节模糊的问题,本文提出一种基于Transformer并用于处理视觉任务的主干网络ConvFormer. ConvFormer通过所设计的多尺度混洗自注意力模块(Channel-Shuffle and Multi-Scale attention,CSMS)和动态相对位置编码模块(Dynamic Relative Position Coding,DRPC)来聚合多尺度像素块间的语义信息,并在前馈网络中引入深度卷积提高网络的局部建模能力.在公开数据集ImageNet-1K,COCO 2017和ADE20K上分别进行图像分类、目标检测和语义分割实验,ConvFormer-Tiny与不同视觉任务中同量级最优网络RetNetY-4G,Swin-Tiny和ResNet50对比,精度分别提高0.3%,1.4%和0.5%.