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 2103.11520cs.CVcs.AI
收藏

无监督自适应跨域身份识别技术

Unsupervised and self-adaptative techniques for cross-domain person re-identification

University of Campinas(坎皮纳斯大学);Institute of Computing(计算机学院)

Gabriel Bertocco, Fernanda Andaló, Anderson Rocha

摘要:

跨非重叠相机的人员重新识别(ReID)是一项具有挑战性的任务,并且由于这个原因,现有技术中的大多数工作依赖于从标记数据集进行的监督特征学习来匹配不同视图中的同一个人。然而,它需要标记所获取的数据的耗时任务,禁止其快速部署,特别是在法医场景中。无监督领域自适应(UDA)是一种很有前途的替代方案,因为它执行从源上训练的模型到目标域的特征学习自适应,而无需身份标签注释。然而,大多数基于UDA的算法依赖于具有多个超参数的复杂损失函数,这阻碍了对不同场景的推广。此外,由于UDA依赖于域之间的转换,因此必须从看不见的域中选择最可靠的数据,从而避免目标数据上的噪声示例引起的错误传播-这是一个经常被忽视的问题。从这个意义上说,我们提出了一种新的基于UDA的ReID方法,该方法优化了一个简单的损失函数,只有一个超参数,并利用了一个新的离线策略创建的样本的三元组基于集群内的相机的多样性。这种新策略调整了模型并对其进行了正则化,避免了目标域上的过拟合。我们还引入了一种新的自集成策略,其中来自不同迭代的权重被聚合以创建一个最终模型,该模型结合了自适应的不同时刻的知识。为了进行评估,我们考虑了三种著名的深度学习架构,并将它们结合起来进行最终决策。所提出的方法不使用人员重新排名,也不使用目标域上的任何标签,并且在Market到Duke,具有挑战性的Market 1501到MSMT 17以及Duke到MSMT 17适应场景中,具有更简单的设置,优于现有技术。

英文摘要:

Person Re-Identification (ReID) across non-overlapping cameras is a challenging task and, for this reason, most works in the prior art rely on supervised feature learning from a labeled dataset to match the same person in different views. However, it demands the time-consuming task of labeling the acquired data, prohibiting its fast deployment, specially in forensic scenarios. Unsupervised Domain Adaptation (UDA) emerges as a promising alternative, as it performs feature-learning adaptation from a model trained on a source to a target domain without identity-label annotation. However, most UDA-based algorithms rely upon a complex loss function with several hyper-parameters, which hinders the generalization to different scenarios. Moreover, as UDA depends on the translation between domains, it is important to select the most reliable data from the unseen domain, thus avoiding error propagation caused by noisy examples on the target data -- an often overlooked problem. In this sense, we propose a novel UDA-based ReID method that optimizes a simple loss function with only one hyper-parameter and that takes advantage of triplets of samples created by a new offline strategy based on the diversity of cameras within a cluster. This new strategy adapts the model and also regularizes it, avoiding overfitting on the target domain. We also introduce a new self-ensembling strategy, in which weights from different iterations are aggregated to create a final model combining knowledge from distinct moments of the adaptation. For evaluation, we consider three well-known deep learning architectures and combine them for final decision-making. The proposed method does not use person re-ranking nor any label on the target domain, and outperforms the state of the art, with a much simpler setup, on the Market to Duke, the challenging Market1501 to MSMT17, and Duke to MSMT17 adaptation scenarios.

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。

↑