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 2006.11486cs.CV
收藏

基于渐进自适应的无监督车辆再识别

Unsupervised Vehicle Re-identification with Progressive Adaptation

Dalian Maritime University(大连海事大学);Pengcheng Laboratory(鹏城实验室);Hefei University of Technology(合肥工业大学)

Jinjia Peng, Yang Wang, Huibing Wang, Zhao Zhang, Xianping Fu, Meng Wang

摘要:

车辆重新识别(reID)旨在识别跨不同非重叠摄像机视图的车辆。现有的方法严重依赖于良好标记的数据集以获得理想的性能,这不可避免地导致由于训练域和真实世界场景之间严重的域偏差而导致的致命下降;更糟糕的是,这些方法需要完整的注释,这是耗费人力的。为了应对这些挑战,我们提出了一种新的渐进式自适应学习方法,称为PAL,它从丰富的数据中推断出没有注释的车辆reID。对于PAL,源域采用数据自适应模块,该模块生成与未标记目标域具有相似数据分布的图像作为"伪目标样本“。这些伪样本与通过动态采样策略选择的未标记样本相结合,以使训练更快。我们进一步提出了加权标签平滑(WLS)损失,该损失考虑了具有不同聚类的样本之间的相似性,以平衡伪标签的置信度。综合实验结果验证了PAL在VehicleID和VeRi-776数据集上的优势。

英文摘要:

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes; worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''. These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset.

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。

↑