Abstract We propose an end-to-end ensemble method for person re-identification (ReID) to address the problem of overfitting in discriminative models. These models are known to converge easily, but they are biased to the training data in general and may produce a high model variance, which is known as overfitting. The ReID task is more prone to this problem due to the large discrepancy between training and test distributions. To address this problem, our proposed ensemble learning framework produces several diverse and accurate base learners in a single DenseNet. Since most of the costly dense blocks are shared, our method is computationally efficient, which makes it favorable compared to the conventional ensemble models. Experiments on several benchmark datasets demonstrate that our method achieves state-of-the-art results. Noticeable performance improvements, especially on relatively small datasets, indicate that the proposed method deals with the overfitting problem effectively.

中文翻译：

---

用于人员重新识别的 CNN 集成的端到端训练

摘要 我们提出了一种用于人员重新识别 (ReID) 的端到端集成方法，以解决判别模型中过度拟合的问题。众所周知，这些模型很容易收敛，但它们通常会偏向于训练数据，并且可能会产生很高的模型方差，这被称为过度拟合。由于训练和测试分布之间的巨大差异，ReID 任务更容易出现此问题。为了解决这个问题，我们提出的集成学习框架在单个 DenseNet 中生成了几个不同且准确的基础学习器。由于大多数昂贵的密集块是共享的，我们的方法在计算上是高效的，这使得它与传统的集成模型相比更有利。在几个基准数据集上的实验表明，我们的方法达到了最先进的结果。