论文标题
弱监督的歧视性特征学习，以及国家信息以供人识别
Weakly supervised discriminative feature learning with state information for person identification
论文作者
论文摘要
在实际的任务中，无监督的身份歧视视觉功能的学习吸引人，在现实世界中，手动标签的成本很高。但是，当在不同状态下拍摄图像时，身份的图像可以在视觉上差异。不同的相机景观和姿势。这种视觉差异导致了无监督的歧视性学习的巨大困难。幸运的是，在实际的任务中，我们经常可以知道没有人类注释的国家，例如我们可以轻松地将相机视图标签亲自重新识别，并在面部识别中具有面部姿势标签。在这项工作中，我们建议利用状态信息作为弱监督，以解决不同状态引起的视觉差异。我们制定了一个简单的伪标签模型，并利用状态信息来尝试通过弱监督的决策边界纠正和弱监督的特征漂移正规化来完善指定的伪标签。我们评估了无监督的人的重新识别和姿势不变的面部识别的模型。尽管我们的方法很简单，但它的表现可以胜过具有标准Resnet-50骨干的Duke-Reid，Multipie和CFP数据集的最先进结果。我们还发现，我们的模型可以与三个数据集中的标准监督微调结果相比执行。代码可从https://github.com/kovenyu/state-information获得
Unsupervised learning of identity-discriminative visual feature is appealing in real-world tasks where manual labelling is costly. However, the images of an identity can be visually discrepant when images are taken under different states, e.g. different camera views and poses. This visual discrepancy leads to great difficulty in unsupervised discriminative learning. Fortunately, in real-world tasks we could often know the states without human annotation, e.g. we can easily have the camera view labels in person re-identification and facial pose labels in face recognition. In this work we propose utilizing the state information as weak supervision to address the visual discrepancy caused by different states. We formulate a simple pseudo label model and utilize the state information in an attempt to refine the assigned pseudo labels by the weakly supervised decision boundary rectification and weakly supervised feature drift regularization. We evaluate our model on unsupervised person re-identification and pose-invariant face recognition. Despite the simplicity of our method, it could outperform the state-of-the-art results on Duke-reID, MultiPIE and CFP datasets with a standard ResNet-50 backbone. We also find our model could perform comparably with the standard supervised fine-tuning results on the three datasets. Code is available at https://github.com/KovenYu/state-information
