Collaborative Refining for Person Re-Identification with Label Noise
Collaborative Refining for Person Re-Identification with Label Noise
复制标题
使用标签噪声进行人员重新识别的协作细化
DOI：
10.1109/tip.2021.3131937
复制
发表时间：
2021
影响因子：
10.6
通讯作者：
S. Hoi
中科院分区：
文献类型：
--
作者：
Mang Ye;He Li;Bo Du;Jianbing Shen;Ling Shao;S. Hoi
现有的行人重新识别（Re-ID）方法通常严重依赖大规模彻底注释的训练数据。然而，由于真实场景中的人物检测结果不准确或标注错误，标签噪声是不可避免的。学习带有标签噪声的鲁棒 Re-ID 模型极具挑战性，因为每个身份的带注释训练样本非常有限。为了避免拟合噪声标签，我们建议在早期阶段使用大学习率和自标签细化策略来学习预模型，其中标签和网络联合优化。为了进一步增强鲁棒性，我们引入了具有动态相互学习的在线协同精炼（CORE）框架，其中网络和标签预测通过从其他对等网络中提取知识来在线协作优化。此外，它还使用有利的选择性一致性策略减少了噪声标签的负面影响。 CORE有两个主要优点：它对不同的噪声类型和未知的噪声比具有鲁棒性；它可以轻松地进行训练，而无需在架构设计上做太多额外的工作。 Re-ID 和图像分类的大量实验表明，CORE 在实际和模拟噪声设置下都大幅优于同类产品。值得注意的是，它还提高了标准设置下最先进的无监督 Re-ID 性能。代码可在 https://github.com/mangye16/ReID-Label-Noise 获取。
Existing person re-identification (Re-ID) methods usually rely heavily on large-scale thoroughly annotated training data. However, label noise is unavoidable due to inaccurate person detection results or annotation errors in real scenes. It is extremely challenging to learn a robust Re-ID model with label noise since each identity has very limited annotated training samples. To avoid fitting to the noisy labels, we propose to learn a prefatory model using a large learning rate at the early stage with a self-label refining strategy, in which the labels and network are jointly optimized. To further enhance the robustness, we introduce an online co-refining (CORE) framework with dynamic mutual learning, where networks and label predictions are online optimized collaboratively by distilling the knowledge from other peer networks. Moreover, it also reduces the negative impact of noisy labels using a favorable selective consistency strategy. CORE has two primary advantages: it is robust to different noise types and unknown noise ratios; it can be easily trained without much additional effort on the architecture design. Extensive experiments on Re-ID and image classification demonstrate that CORE outperforms its counterparts by a large margin under both practical and simulated noise settings. Notably, it also improves the state-of-the-art unsupervised Re-ID performance under standard settings. Code is available at https://github.com/mangye16/ReID-Label-Noise.