Deep Metric Learning with Online Hard and Soft Selection for Person Re-identification
2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR)(2018)
摘要
Deep metric learning has been widely used for image retrieval and verification tasks. Traditional contrastive loss and triplet loss depend highly on the selection of pair/triplet images. It makes the training process unstable and uncomplete. In this paper, we propose a novel global level loss function that considers histograms for intra distances within class and inter distances between different classes. We compared two forms of global level loss (hard selection based loss and soft selection based loss) and both achieved better result than traditional triplet loss, multi-class N pair loss and other related works. The experiment is conducted on the person re-identification dataset Market 1501 and DukeMTMC-reID.
更多查看译文
关键词
Histograms,Training,Task analysis,Euclidean distance,Feature extraction,Image retrieval
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络