论文标题
在重新识别的后期学习后部和事先进行不确定性建模
Learning Posterior and Prior for Uncertainty Modeling in Person Re-Identification
论文作者
论文摘要
实际人REID的数据不确定性无处不在，因此它不仅需要学习判别特征，而且还需要基于输入的不确定性进行建模。本文提议学习潜在空间中的样本后部和类先验分布，因此不仅代表性特征，而且不确定性可以由模型构建。先验反映了同一类中所有数据的分布，它是可训练的模型参数。虽然后验是单个样本的概率密度，因此实际上是输入中定义的特征。我们假设他们俩都是高斯形式。为了同时对它们进行建模，我们提出了分配损失，该分配损失以监督学习方式来衡量KL从后向先验的差异。此外，我们假设后差本质上是不确定性，应该具有二阶特征。因此，提出了一个$σ-$ net，以通过其输入来计算高阶表示。在Market1501，Dukemtmc，Mars和Noisy数据集上进行了广泛的实验。
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.
