论文标题
通过回归检索进行无监督的人群计数双重知识转移
Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer
论文作者
论文摘要
无监督的人群计数是一个具有挑战性的人，但并未在很大程度上探讨。在本文中，我们在转移学习环境中探讨了它，我们通过转移从标记的源集中从基于回归和检测的模型中学到的双重知识来检测和计算未标记目标集中的人。这两个模型的双重源知识是异构和互补的，因为它们捕获了人群分布的不同方式。我们将基于回归模型和基于检测的模型的输出之间的相互转换作为两个场景敏捷的变压器，从而实现了两个模型之间的知识蒸馏。鉴于基于回归和检测的模型及其在源中学到的共同变压器，我们引入了目标中迭代的自学学习方案，并在目标中带有回归检测的双重知识转移。对标准人群计数基准，上海，UCF \ _CC \ _50和UCF \ _QNRF进行了广泛的实验，这表明我们的方法比转移学习环境中的其他最先进的方法进行了实质性改进。
Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge learnt from regression- and detection-based models in a labeled source set. The dual source knowledge of the two models is heterogeneous and complementary as they capture different modalities of the crowd distribution. We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models. Given the regression- and detection-based models and their mutual transformers learnt in the source, we introduce an iterative self-supervised learning scheme with regression-detection bi-knowledge transfer in the target. Extensive experiments on standard crowd counting benchmarks, ShanghaiTech, UCF\_CC\_50, and UCF\_QNRF demonstrate a substantial improvement of our method over other state-of-the-arts in the transfer learning setting.
