摘要
在跨场景、跨设备的行人重识别中虽然增加了可利用的行人数据,但由于行人姿态不同、部分遮挡现象,难以避免引入样本噪声,在聚类过程中易生成错误的伪标签,造成标签噪声,影响模型的优化。为减弱噪声影响,应用相机感知的距离矩阵对抗相机偏移引起的样本噪声问题,利用对噪声鲁棒的动态对称对比损失减少标签噪声,提出基于相机感知距离矩阵的无监督行人重识别算法。在聚类前通过更改度量行人特征相似度的距离矩阵,利用相机感知距离矩阵来增强类内距离度量准确性,减少由于拍摄视角不同对聚类效果造成的负面影响。同时,结合噪声标签学习方法,进行损失设计,提出动态对称对比损失函数,联合损失训练,不断精炼伪标签。在DukeMTMC-reID和Market-1501两个数据集上进行实验,验证了提出方法的有效性。
Cross‑scene and cross-device shooting greatly increases the data of pedestrians.However,due to the different postures and partial occlusion of pedestrians,it is difficult to avoid the introduction of sample noise.During the clustering process,it is easy to generate false pseudo-labels,resulting in label noise and affecting the optimization of the model.In order to reduce the influence of noise,the cameraaware distance matrix is applied to combat the sample noise problem caused by camera offset,and the noise-robust dynamic symmetric contrast loss is used to reduce label noise.Specifically,the distance matrix that measures the similarity of pedestrian features is changed before clustering,and the camera-aware distance matrix is used to enhance the accuracy of the intra-class distance measurement,reducing the negative impact of different perspectives on the clustering effect.Combined with the noise label learning method,a robust loss is designed,a dynamic symmetric contrast loss function is proposed,and a joint loss training is used to continuously refine the pseudo-labels.Experiments are carried out on DukeMTMC-reID and Market-1501 datasets to verify the effectiveness of the proposed method.
作者
白梦林
周非
舒浩峰
BAI Menglin;ZHOU Fei;SHU Haofeng(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)
出处
《数据采集与处理》
CSCD
北大核心
2023年第5期1069-1078,共10页
Journal of Data Acquisition and Processing
基金
国家自然科学基金(61901071)。
关键词
无监督行人重识别
聚类
距离矩阵
标签噪声
损失函数
unsupervised person re-identification
clustering
distance matrix
labels noise
loss function
