Deep triplet-group network by exploiting symmetric and asymmetric information for person reidentification.
JOURNAL OF ELECTRONIC IMAGING(2018)
摘要
Deep metric learning is an effective method for person reidentification. In practice, impostor samples generally possess more discriminative information than other negative samples. Specifically, existing triplet-based deep-learning methods cannot effectively remove impostors, because they cannot consider congeners of impostor and it may produce new impostors when removing existing impostors. To utilize discriminative information in triplets and make impostor and its congeners more clustering, we design oversymmetric and over-asymmetric relationships and apply these two constraints to triplet and impostors' congeners to train our deep triplet-group network with original individual images rather than handcrafted features. Extensive experiments with five benchmark datasets demonstrate that our method outperforms the state-of-the-art methods with regards to the rank-N matching accuracy.(C) The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License.
更多查看译文
关键词
person reidentification,deep metric learning,deep learning,impostor,symmetric and asymmetric information
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络