论文标题
无监督人员重新识别的多层次关注
Multi-Level Attention for Unsupervised Person Re-Identification
论文作者
论文摘要
注意机制在深度学习中广泛使用，因为它在神经网络中的出色表现而没有引入其他信息。但是，在无监督的人的重新识别中，由多头自我发场代表的注意模块在非地面真理的条件下遭受了关注。为了解决这个问题，我们设计了像素级的注意模块，以提供多头自我注意的限制。同时，对于人重新识别数据的识别目标都是样本中的行人，我们设计了域级的注意模块以提供更全面的行人特征。我们结合了头部级，像素级和域级的关注，以提出多层次的注意力块，并验证大人重新识别数据集（Market-1501，Dukemtmc-Reid，MSMT17和MSMT17和Personx）的性能。
The attention mechanism is widely used in deep learning because of its excellent performance in neural networks without introducing additional information. However, in unsupervised person re-identification, the attention module represented by multi-headed self-attention suffers from attention spreading in the condition of non-ground truth. To solve this problem, we design pixel-level attention module to provide constraints for multi-headed self-attention. Meanwhile, for the trait that the identification targets of person re-identification data are all pedestrians in the samples, we design domain-level attention module to provide more comprehensive pedestrian features. We combine head-level, pixel-level and domain-level attention to propose multi-level attention block and validate its performance on for large person re-identification datasets (Market-1501, DukeMTMC-reID and MSMT17 and PersonX).
