arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.06779cs.CV
收藏

步态识别中的广义类间损失

Generalized Inter-class Loss for Gait Recognition

Watrix(银河水滴);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

Weichen Yu, Hongyuan Yu, Yan Huang, Liang Wang

摘要:

步态识别是一种独特的生物特征识别技术,可以在远距离非合作地进行,在公共安全和智能交通系统中有着广泛的应用。以往的步态算法更多地关注类内方差的最小化,而忽略了约束类间方差的重要性。为此,我们提出了一个广义的类间损失,解决了样本级特征分布和类级特征分布的类间方差。而不是相等的惩罚强度对得分,建议的损失优化样本级的类间特征分布,通过动态调整成对的权重。此外,在类级分布中,广义类间损失增加了对类间特征分布均匀性的约束,这迫使特征表示近似于超球面并保持最大类间方差。此外,所提出的方法自动调整类之间的差距,使类间的特征分布更加灵活。该方法可以推广到不同的步态识别网络,并取得了显着的改善。我们在CASIA-B和OUMVLP上进行了一系列的实验,实验结果表明,提出的损耗可以显著提高性能,达到了最先进的性能。

英文摘要:

Gait recognition is a unique biometric technique that can be performed at a long distance non-cooperatively and has broad applications in public safety and intelligent traffic systems. Previous gait works focus more on minimizing the intra-class variance while ignoring the significance in constraining inter-class variance. To this end, we propose a generalized inter-class loss which resolves the inter-class variance from both sample-level feature distribution and class-level feature distribution. Instead of equal penalty strength on pair scores, the proposed loss optimizes sample-level inter-class feature distribution by dynamically adjusting the pairwise weight. Further, in class-level distribution, generalized inter-class loss adds a constraint on the uniformity of inter-class feature distribution, which forces the feature representations to approximate a hypersphere and keep maximal inter-class variance. In addition, the proposed method automatically adjusts the margin between classes which enables the inter-class feature distribution to be more flexible. The proposed method can be generalized to different gait recognition networks and achieves significant improvements. We conduct a series of experiments on CASIA-B and OUMVLP, and the experimental results show that the proposed loss can significantly improve the performance and achieves the state-of-the-art performances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑