论文标题
无监督的域自适应人员重新识别的学习功能融合
Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification
论文作者
论文摘要
无监督的领域自适应（UDA）人重新识别（REID）在没有手动注释的情况下对目标域的有效性引起了人们的关注。大多数基于微调的UDA人REID方法着重于编码伪标签的全局功能，忽略了可以提供细粒信息的本地功能。为了解决这个问题，我们提出了一个学习功能融合（LF2）框架，以自适应地学习融合全球和本地功能，以获得更全面的融合功能表示。具体而言，我们首先在源域内预先培训我们的模型，然后根据教师培训策略对未标记的目标域进行微调模型。平均加权教师网络旨在编码全局功能，而在每次迭代时进行更新的学生网络负责良好的本地功能。通过融合这些多视图功能，采用多级聚类来生成多种伪标签。特别是，还提出了一个可学习的融合模块（FM），以使全球功能中的细粒度本地信息突出，以避免掩盖多个伪标签的学习。实验表明，我们提出的LF2框架的表现优于最先进的MAP，Market1501的73.5％MAP和83.7％的级别在Dukemtmc-Reid上优于Market1501，并在DUKEMTMC-REID上获得83.2％的MAP和92.8％的MAP和92.8％的RANK1。
Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods focus on encoding global features for pseudo labels generation, neglecting the local feature that can provide for the fine-grained information. To handle this issue, we propose a Learning Feature Fusion (LF2) framework for adaptively learning to fuse global and local features to obtain a more comprehensive fusion feature representation. Specifically, we first pre-train our model within a source domain, then fine-tune the model on unlabeled target domain based on the teacher-student training strategy. The average weighting teacher network is designed to encode global features, while the student network updating at each iteration is responsible for fine-grained local features. By fusing these multi-view features, multi-level clustering is adopted to generate diverse pseudo labels. In particular, a learnable Fusion Module (FM) for giving prominence to fine-grained local information within the global feature is also proposed to avoid obscure learning of multiple pseudo labels. Experiments show that our proposed LF2 framework outperforms the state-of-the-art with 73.5% mAP and 83.7% Rank1 on Market1501 to DukeMTMC-ReID, and achieves 83.2% mAP and 92.8% Rank1 on DukeMTMC-ReID to Market1501.
