ReadNet : 使用有限的带噪样本实现精准（ReID）行人重识别（cs.CV）---Donuts_choco

行人重新识别 （ReID） 是识别行人的基本交叉摄像头检索任务。然而，每位行人的照片数量通常差别很大，因此数据限制和不平衡问题大大阻碍了预测的准确性。此外，在实际应用中，行人图像由不同的监控摄像机捕获，因此带噪的摄像机相关信息（如灯光、透视和分辨率）会在 ReID 算法上产生难以避免的域差距。这些困难给予了目前的深度学习方法以挑战。在应对此类问题时，算法损失会扩大三倍。为了应对这些挑战，本文提出了ReadNet，一个具有角三重损耗（ATL）的对抗性摄像机网络（ACN）。具体来说，ATL专注于了解不同实体之间的角度距离，以减轻数据不平衡的影响，并保证线性决策边界，而ACN则将相机鉴别器作为特征提取器的博弈对手，以过滤摄像机相关信息，以连接多摄像机间隙。ReadNet 设计灵活以求ATL 或 ACN 可以独立或同时部署。对各种基准数据集的实验结果表明，ReadNet 可以提供比当前最先进的方法更好的预测性能。

原文标题：ReadNet:Towards Accurate ReID with Limited and Noisy Samples

原文：Person re-identification (ReID) is an essential cross-camera retrieval task to identify pedestrians. However, the photo number of each pedestrian usually differs drastically, and thus the data limitation and imbalance problem hinders the prediction accuracy greatly. Additionally, in real-world applications, pedestrian images are captured by different surveillance cameras, so the noisy camera related information, such as the lights, perspectives and resolutions, result in inevitable domain gaps for ReID algorithms. These challenges bring difficulties to current deep learning methods with triplet loss for coping with such problems. To address these challenges, this paper proposes ReadNet, an adversarial camera network (ACN) with an angular triplet loss (ATL). In detail, ATL focuses on learning the angular distance among different identities to mitigate the effect of data imbalance, and guarantees a linear decision boundary as well, while ACN takes the camera discriminator as a game opponent of feature extractor to filter camera related information to bridge the multi-camera gaps. ReadNet is designed to be flexible so that either ATL or ACN can be deployed independently or simultaneously. The experiment results on various benchmark datasets have shown that ReadNet can deliver better prediction performance than current state-of-the-art methods.

原文作者：Yitian Li, Ruini Xue, Mengmeng Zhu, Qing Xu, Zenglin Xu

原文地址：http://arxiv.org/abs/2005.05740