DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning
DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning
复制标题
DotSCN：通过域转移的单个和情侣表示学习进行群体重新识别
DOI：
10.1109/tcsvt.2020.3031303
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Chia-Wen Lin and Shin'ichi Satoh
中科院分区：
文献类型：
--
作者：
Ziling Huang;Zheng Wang;Wei Hu;Chia-Wen Lin and Shin'ichi Satoh
群重识别（G-ReID）是一个重要但研究较少的任务。它的挑战不仅在于个人的外观变化，而且涉及群体布局和成员的变化。为了解决这些问题，G-ReID的关键任务是学习对这些变化具有鲁棒性的组表示。然而，与ReID任务不同的是，仍然缺乏全面的公开可用的G-ReID数据集，因此很难使用深度学习模型来学习有效的表示。在这篇文章中，我们提出了一个域转移的单一和耦合表示学习网络（DotSCN）。它的优点有两个方面：1）由于缺乏用于G-ReID的标记训练样本，现有的G-ReID方法主要依赖于不令人满意的手工特征。为了获得深度学习模型在表示学习中的能力，我们首先将一个群体视为多个个体的集合，并建议将从现有标记的ReID数据集学习到的个体表示转移到目标G-ReID域，而无需合适的训练数据集。2)考虑到组中的邻域关系，我们进一步提出学习两个组成员之间的新的耦合表示，在G-ReID任务中实现更好的区分能力。此外，我们提出了一个权重学习方法，自适应融合域转移的个人和夫妇表示的基础上的L形先验。大量的实验结果表明，我们的方法的有效性，显着优于国家的最先进的方法由11.7% CMC-1的道路组数据集和39.0% CMC-1的DukeMCMT数据集。
Group re-identification (G-ReID) is an important yet less-studied task. Its challenges not only lie in appearance changes of individuals, but also involve group layout and membership changes. To address these issues, the key task of G-ReID is to learn group representations robust to such changes. Nevertheless, unlike ReID tasks, there still lacks comprehensive publicly available G-ReID datasets, making it difficult to learn effective representations using deep learning models. In this article, we propose a Domain-Transferred Single and Couple Representation Learning Network (DotSCN). Its merits are two aspects: 1) Owing to the lack of labelled training samples for G-ReID, existing G-ReID methods mainly rely on unsatisfactory hand-crafted features. To gain the power of deep learning models in representation learning, we first treat a group as a collection of multiple individuals and propose transferring the representation of individuals learned from an existing labeled ReID dataset to a target G-ReID domain without a suitable training dataset. 2) Taking into account the neighborhood relationship in a group, we further propose learning a novel couple representation between two group members, that achieves better discriminative power in G-ReID tasks. In addition, we propose a weight learning method to adaptively fuse the domain-transferred individual and couple representations based on an L-shape prior. Extensive experimental results demonstrate the effectiveness of our approach that significantly outperforms state-of-the-art methods by 11.7% CMC-1 on the Road Group dataset and by 39.0% CMC-1 on the DukeMCMT dataset.