Visible-infrared person re-identification(VIPR), is a cross-modal retrieval task that searches a target from a gallery captured by cameras of different spectrums.The severe challenge for VIPR is the large intra-class ...Visible-infrared person re-identification(VIPR), is a cross-modal retrieval task that searches a target from a gallery captured by cameras of different spectrums.The severe challenge for VIPR is the large intra-class variation caused by the modal discrepancy between visible and infrared images.For that, this paper proposes a query related cluster(QRC) method for VIPR.Firstly, this paper uses an attention mechanism to calculate the similarity relation between a visible query and infrared images with the same identity in the gallery.Secondly, those infrared images with the same query images are aggregated by using the similarity relation to form a dynamic clustering center corresponding to the query image.Thirdly, QRC loss function is designed to enlarge the similarity between the query image and its dynamic cluster center to achieve query related clustering, so as to compact the intra-class variations.Consequently, in the proposed QRC method, each query has its own dynamic clustering center, which can well characterize intra-class variations in VIPR.Experimental results demonstrate that the proposed QRC method is superior to many state-of-the-art approaches, acquiring a 90.77% rank-1 identification rate on the RegDB dataset.展开更多
针对当前跨模态行人重识别算法大多聚类能力不强、且难以提取高效辨别性特征的问题,提出了一种多粒度跨模态行人重识别算法。首先,在骨干网络Resnet50中加入非局部注意力机制模块,关注长距离像素之间的关系,保留细节信息;其次,采用多分...针对当前跨模态行人重识别算法大多聚类能力不强、且难以提取高效辨别性特征的问题,提出了一种多粒度跨模态行人重识别算法。首先,在骨干网络Resnet50中加入非局部注意力机制模块,关注长距离像素之间的关系,保留细节信息;其次,采用多分支网络提取不同细粒度特征信息,增强模型的辨别性特征提取能力;最后,联合基于样本的三元组损失和基于中心的三元组损失监督训练,加速模型收敛。所提算法在SYSU-MM01数据集的全搜索模式下Rank-1和mean average precision分别达到62.83%和58.10%,在RegDB数据集的可见光到红外模式下Rank-1和mAP分别达到87.78%和76.22%。展开更多
现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性。因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法。首先,提出...现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性。因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法。首先,提出基于对比学习框架的预训练方法,利用可见光行人图像和其生成的辅助灰度图像进行训练。利用该预训练方法获取对颜色变化具有鲁棒性的语义特征提取网络。然后,使用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)聚类方法生成语义伪标签。相比现有的伪标签生成方法,文中提出的语义伪标签在生成过程中充分利用跨模态数据之间的结构信息,减少跨模态数据颜色变化带来的模态差异。此外,文中还构建实例级困难样本特征存储库和中心级聚类特征存储库,充分利用困难样本特征和聚类特征,让模型对噪声伪标签具有更强的鲁棒性。在SYSU-MM01、RegDB两个跨模态数据集上的实验验证文中方法的有效性。展开更多
基金Supported by the National Natural Science Foundation of China (No.61976098)the Natural Science Foundation for Outstanding Young Scholars of Fujian Province (No.2022J06023)。
文摘Visible-infrared person re-identification(VIPR), is a cross-modal retrieval task that searches a target from a gallery captured by cameras of different spectrums.The severe challenge for VIPR is the large intra-class variation caused by the modal discrepancy between visible and infrared images.For that, this paper proposes a query related cluster(QRC) method for VIPR.Firstly, this paper uses an attention mechanism to calculate the similarity relation between a visible query and infrared images with the same identity in the gallery.Secondly, those infrared images with the same query images are aggregated by using the similarity relation to form a dynamic clustering center corresponding to the query image.Thirdly, QRC loss function is designed to enlarge the similarity between the query image and its dynamic cluster center to achieve query related clustering, so as to compact the intra-class variations.Consequently, in the proposed QRC method, each query has its own dynamic clustering center, which can well characterize intra-class variations in VIPR.Experimental results demonstrate that the proposed QRC method is superior to many state-of-the-art approaches, acquiring a 90.77% rank-1 identification rate on the RegDB dataset.
文摘针对当前跨模态行人重识别算法大多聚类能力不强、且难以提取高效辨别性特征的问题,提出了一种多粒度跨模态行人重识别算法。首先,在骨干网络Resnet50中加入非局部注意力机制模块,关注长距离像素之间的关系,保留细节信息;其次,采用多分支网络提取不同细粒度特征信息,增强模型的辨别性特征提取能力;最后,联合基于样本的三元组损失和基于中心的三元组损失监督训练,加速模型收敛。所提算法在SYSU-MM01数据集的全搜索模式下Rank-1和mean average precision分别达到62.83%和58.10%,在RegDB数据集的可见光到红外模式下Rank-1和mAP分别达到87.78%和76.22%。
文摘现有的有监督可见光-近红外行人重识别方法需要大量人力资源去除手工标注数据,容易受到标注数据场景的限制,难以满足真实多变应用场景的泛化性。因此,文中提出基于语义伪标签和双重特征存储库的无监督跨模态行人重识别方法。首先,提出基于对比学习框架的预训练方法,利用可见光行人图像和其生成的辅助灰度图像进行训练。利用该预训练方法获取对颜色变化具有鲁棒性的语义特征提取网络。然后,使用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)聚类方法生成语义伪标签。相比现有的伪标签生成方法,文中提出的语义伪标签在生成过程中充分利用跨模态数据之间的结构信息,减少跨模态数据颜色变化带来的模态差异。此外,文中还构建实例级困难样本特征存储库和中心级聚类特征存储库,充分利用困难样本特征和聚类特征,让模型对噪声伪标签具有更强的鲁棒性。在SYSU-MM01、RegDB两个跨模态数据集上的实验验证文中方法的有效性。
