论文标题
参数共享探索和基于异构中心的三胞胎损失可见的人重新识别
Parameter Sharing Exploration and Hetero-Center based Triplet Loss for Visible-Thermal Person Re-Identification
论文作者
论文摘要
本文重点介绍了可见的热跨模式人员重新识别（VT RE-ID）任务，其目标是在白天可见的方式和夜间热模式之间匹配人的图像。通过学习多模式的人的特征，通常采用两流网络来解决VT RE-ID的交叉模式差异，这是VT Re-ID最具挑战性的问题。在本文中，我们探讨了应共享的两流网络的数量参数，这在现有文献中仍未得到很好的研究。通过对RESNET50模型进行良好的分解以构建特定于模态的特征提取网络和模态共享特征嵌入网络，我们实验表明了VT RE-ID的两流网络的参数共享的效果。此外，在零件级人员特征学习的框架中，我们提出了基于异内中心的三胞胎损失，以放大传统三胞胎损失的严格限制，通过替换锚固中心与所有其他中心的所有其他样本的比较，从而严格限制。借助非常简单的手段，提出的方法可以显着改善VT重新ID性能。两个数据集上的实验结果表明，我们提出的方法明显优于最先进的方法，尤其是在REGDB数据集上，rank1/rank1/map/minp 91.05％/83.28％/68.84％。通过简单但有效的策略，它可能是VT Re-ID的新基线。
This paper focuses on the visible-thermal cross-modality person re-identification (VT Re-ID) task, whose goal is to match person images between the daytime visible modality and the nighttime thermal modality. The two-stream network is usually adopted to address the cross-modality discrepancy, the most challenging problem for VT Re-ID, by learning the multi-modality person features. In this paper, we explore how many parameters of two-stream network should share, which is still not well investigated in the existing literature. By well splitting the ResNet50 model to construct the modality-specific feature extracting network and modality-sharing feature embedding network, we experimentally demonstrate the effect of parameters sharing of two-stream network for VT Re-ID. Moreover, in the framework of part-level person feature learning, we propose the hetero-center based triplet loss to relax the strict constraint of traditional triplet loss through replacing the comparison of anchor to all the other samples by anchor center to all the other centers. With the extremely simple means, the proposed method can significantly improve the VT Re-ID performance. The experimental results on two datasets show that our proposed method distinctly outperforms the state-of-the-art methods by large margins, especially on RegDB dataset achieving superior performance, rank1/mAP/mINP 91.05%/83.28%/68.84%. It can be a new baseline for VT Re-ID, with a simple but effective strategy.
