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 2007.08785cs.CV
收藏

人员再识别中不确定性建模的后验和先验学习

Learning Posterior and Prior for Uncertainty Modeling in Person Re-Identification

East China Normal University(华东师范大学)

Yan Zhang, Zhilin Zheng, Binyu He, Li Sun

摘要:

数据的不确定性在实际的人reID是普遍存在的,因此它不仅需要学习的区别性的功能,但也基于输入的不确定性建模。本文提出在潜空间中学习样本的后验分布和类别的先验分布,使得模型既能建立代表性特征,又能建立不确定性特征。先验反映了所有数据在同一类中的分布,是可训练的模型参数。而后验是单个样本的概率密度,因此它实际上是在输入上定义的特征。我们假设它们都是高斯形式。为了同时对它们进行建模,我们提出了一种分布损失,它以监督学习的方式测量从后验到先验的KL分歧。此外,我们假设后验方差,这是本质上的不确定性,应该有二阶特性。因此,提出了一个$Σ-$网,从其输入的高阶表示来计算它。在Market1501、DukeMTMC、MARS和噪声数据集上进行了大量的实验。

英文摘要:

Data uncertainty in practical person reID is ubiquitous, hence it requires not only learning the discriminative features, but also modeling the uncertainty based on the input. This paper proposes to learn the sample posterior and the class prior distribution in the latent space, so that not only representative features but also the uncertainty can be built by the model. The prior reflects the distribution of all data in the same class, and it is the trainable model parameters. While the posterior is the probability density of a single sample, so it is actually the feature defined on the input. We assume that both of them are in Gaussian form. To simultaneously model them, we put forward a distribution loss, which measures the KL divergence from the posterior to the priors in the manner of supervised learning. In addition, we assume that the posterior variance, which is essentially the uncertainty, is supposed to have the second-order characteristic. Therefore, a $Σ-$net is proposed to compute it by the high order representation from its input. Extensive experiments have been carried out on Market1501, DukeMTMC, MARS and noisy dataset as well.

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。

↑