论文标题
通过无监督人员重新识别的不对称分支来增强教师学生网络的多样性
Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
论文作者
论文摘要
无监督人员重新识别（RE-ID）的目的是学习歧视性特征，而没有劳动密集型的身份注释。最先进的无监督重新ID方法将伪标签分配给目标域中未标记的图像，并从这些嘈杂的伪标签中学习。最近引入的平均教师模型是减轻标签噪声的一种有希望的方法。但是，在培训期间，自我赞扬的教师 - 学生网络迅速汇聚成共识，这导致了当地的最低限度。我们探讨了在神经网络内使用不对称结构来解决此问题的可能性。首先，提出了不对称分支以不同的方式提取特征，从而增强了外观特征的特征多样性。然后，我们提出的跨分支监督允许一个分支从另一个分支机构获得监督，该分支转移了不同的知识并增强了教师和学生网络之间的体重多样性。广泛的实验表明，我们提出的方法可以显着超过对无监督的域适应和完全无监督的重新ID任务的先前工作的表现。
The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations. State-of-the-art unsupervised Re-ID methods assign pseudo labels to unlabeled images in the target domain and learn from these noisy pseudo labels. Recently introduced Mean Teacher Model is a promising way to mitigate the label noise. However, during the training, self-ensembled teacher-student networks quickly converge to a consensus which leads to a local minimum. We explore the possibility of using an asymmetric structure inside neural network to address this problem. First, asymmetric branches are proposed to extract features in different manners, which enhances the feature diversity in appearance signatures. Then, our proposed cross-branch supervision allows one branch to get supervision from the other branch, which transfers distinct knowledge and enhances the weight diversity between teacher and student networks. Extensive experiments show that our proposed method can significantly surpass the performance of previous work on both unsupervised domain adaptation and fully unsupervised Re-ID tasks.
