跨模态行人重识别研究的重难点主要来自于行人图像之间巨大的模态差异和模态内差异.针对这些问题,提出一种结合多尺度特征与混淆学习的网络结构.为实现高效的特征提取、缩小模态内差异,将网络设计为多尺度特征互补的形式,分别学习行人的局部细化特征与全局粗糙特征,从细粒度和粗粒度两方面来增强网络的特征表达能力.利用混淆学习策略,模糊网络的模态识别反馈,挖掘稳定且有效的模态无关属性应对模态差异,来提高特征对模态变化的鲁棒性.在大规模数据集SYSU-MM01 的全搜索模式下该算法首位击中率和平均精度(mean average precision,mAP)的结果分别为 76.69%和 72.45%,在RegDB数据集的可见光到红外模式下该算法首位击中率和mAP的结果分别为94.62%和94.60%,优于现有的主要方法,验证了所提方法的有效性.
Abstract
The difficulties of cross-modal person re-identification research mainly come from the huge modal differ-ences and intra-modal differences between pedestrian images.To address these issues,a network structure combining multi-scale features with obfuscation learning is proposed.In order to achieve high-efficiency feature extraction and re-duce intra-modal differences,the network is designed as a complementary form of multi-scale features to learn local re-finement features and global rough features of pedestrians respectively.The feature expression ability of the network is enhanced from fine-grained and coarse-grained aspects.Confusion learning strategy is used to fuzzy the modal identific-ation feedback of the network,and mine the stable and effective modal-independent attributes to cope with modal differ-ences,so as to improve the robustness of features to modal changes.In the all-search mode of the large-scale data set SYSU-MM01,the results of the first hit rate and mean average precision(mAP)of the algorithm are 76.69%and 72.45%,respectively.In the Visible to Infrared mode of the RegDB data set,the results of the first hit rate and mAP of the algorithm are 94.62%and 94.60%,respectively,which are better than the main existing methods,verifying effective-ness of the proposed method.
维普
万方数据