当前位置: X-MOL 学术Int. J. Pattern Recognit. Artif. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A New Deep Learning Method Based on Unsupervised Domain Adaptation and Re-ranking in Person Re-identification
International Journal of Pattern Recognition and Artificial Intelligence ( IF 1.5 ) Pub Date : 2020-01-31 , DOI: 10.1142/s0218001420520114
Chunhui Wang 1 , Hua Han 1 , Xiwu Shang 1 , Xiaoli Zhao 1
Affiliation  

Person re-identification (Re-ID) is a research hot spot in the field of intelligent video analysis, and it is also a challenging task. As the number of samples grows larger, traditional metric and feature learning methods fall into bottleneck, while it just meets the needs of deep learning algorithm, which perform very well in person re-identification. Although they have achieved good results in the field of supervised learning, their application in real-world scenarios is not very satisfactory. This is mainly because in the real world, a huge number of labeled images are hard to obtain, and even if they are obtained, the cost is expensive. Meanwhile, the performance of deep learning in unsupervised metrics is not ideal. For solving the problem, we propose a new method based on unsupervised domain adaptation (UDA) and re-ranking, and name it UDA[Formula: see text]. As for this method, we first train a camera-aware style transfer model to gain camstyle images. Then we further reduce the difference between the domain of the target and source by using invariant feature, and further improve their commonality. In addition, re-ranking is also introduced to optimize the matching results. This method can not only reduce the cost of obtaining labeled data, but also improve the accuracy. Experimental results show that our method can outperform the most advanced method by 4% on Rank-1 and 14% on mAP. The results also better confirm the effectiveness of Re-ranking module and provide a new idea for domain adaptation by unsupervised methods in the future.

中文翻译:

一种基于无监督域自适应和重排序的人重识别深度学习新方法

行人重识别(Re-ID)是智能视频分析领域的研究热点,也是一项具有挑战性的任务。随着样本数量的增长,传统的度量和特征学习方法陷入瓶颈,而它恰好满足深度学习算法的需求,在行人再识别方面表现非常好。虽然它们在监督学习领域取得了不错的成绩,但在现实世界场景中的应用却不是很理想。这主要是因为在现实世界中,海量的标注图像很难获得,即使获得,成本也很高。同时,深度学习在无监督指标中的表现并不理想。为了解决这个问题,我们提出了一种基于无监督域适应(UDA)和重新排序的新方法,并将其命名为 UDA[公式:见正文]。对于这种方法,我们首先训练一个相机感知风格转移模型来获得 camstyle 图像。然后我们通过使用不变特征进一步减少目标域和源域之间的差异,进一步提高它们的共性。此外,还引入了重新排序来优化匹配结果。这种方法不仅可以降低获取标记数据的成本,而且可以提高准确率。实验结果表明,我们的方法在 Rank-1 上的性能比最先进的方法高 4%,在 mAP 上的性能高出 14%。该结果也更好地证实了 Re-ranking 模块的有效性,并为未来通过无监督方法进行域适应提供了新思路。然后我们通过使用不变特征进一步减少目标域和源域之间的差异,进一步提高它们的共性。此外,还引入了重新排序来优化匹配结果。这种方法不仅可以降低获取标记数据的成本,而且可以提高准确率。实验结果表明,我们的方法在 Rank-1 上的性能比最先进的方法高 4%,在 mAP 上的性能高出 14%。该结果也更好地证实了 Re-ranking 模块的有效性,并为未来通过无监督方法进行域适应提供了新思路。然后我们通过使用不变特征进一步减少目标域和源域之间的差异,进一步提高它们的共性。此外,还引入了重新排序来优化匹配结果。这种方法不仅可以降低获取标记数据的成本,而且可以提高准确率。实验结果表明,我们的方法在 Rank-1 上的性能比最先进的方法高 4%,在 mAP 上的性能高出 14%。该结果也更好地证实了 Re-ranking 模块的有效性,并为未来通过无监督方法进行域适应提供了新思路。这种方法不仅可以降低获取标记数据的成本,而且可以提高准确率。实验结果表明,我们的方法在 Rank-1 上的性能比最先进的方法高 4%,在 mAP 上的性能高出 14%。该结果也更好地证实了 Re-ranking 模块的有效性,并为未来通过无监督方法进行域适应提供了新思路。这种方法不仅可以降低获取标记数据的成本,而且可以提高准确率。实验结果表明,我们的方法在 Rank-1 上的性能比最先进的方法高 4%,在 mAP 上的性能高出 14%。该结果也更好地证实了 Re-ranking 模块的有效性,并为未来通过无监督方法进行域适应提供了新思路。
更新日期:2020-01-31
down
wechat
bug