用于无监督行人重识别的自适应类内变化对比学习
Adaptive Intra-Class Variation Contrastive Learning for Unsupervised Person Re-Identification
AI总结：
针对无监督行人重识别中记忆更新、假阳性样本及离群点丢弃问题，提出 AdaInCV 算法，通过 AdaSaM 与 AdaOF 自适应选择样本并利用有价值离群点。
摘要：
基于记忆字典的对比学习方法已在无监督行人重识别（Re-ID）领域取得显著成果。然而，基于所有样本更新记忆的方法未能充分利用最难样本来提升模型的泛化能力，而基于最难样本挖掘的方法又不可避免地会在模型早期引入被错误聚类的假阳性样本。基于聚类的方法通常会丢弃大量离群点，导致有价值信息的丢失。为解决上述问题，我们提出了一种用于无监督 Re-ID 的自适应类内变化对比学习算法，名为 AdaInCV。该算法通过考虑聚类后的类内变化，定量评估模型对每个类别的学习能力，从而有助于在模型训练过程中选择合适的样本。具体而言，我们提出了两种新策略：自适应样本挖掘（AdaSaM）和自适应离群点过滤器（AdaOF）。前者逐步建立更可靠的聚类以动态优化记忆，而后者能够识别并筛选出有价值的离群点作为负样本。
英文摘要：
The memory dictionary-based contrastive learning method has achieved remarkable results in the field of unsupervised person Re-ID. However, The method of updating memory based on all samples does not fully utilize the hardest sample to improve the generalization ability of the model, and the method based on hardest sample mining will inevitably introduce false-positive samples that are incorrectly clustered in the early stages of the model. Clustering-based methods usually discard a significant number of outliers, leading to the loss of valuable information. In order to address the issues mentioned before, we propose an adaptive intra-class variation contrastive learning algorithm for unsupervised Re-ID, called AdaInCV. And the algorithm quantitatively evaluates the learning ability of the model for each class by considering the intra-class variations after clustering, which helps in selecting appropriate samples during the training process of the model. To be more specific, two new strategies are proposed: Adaptive Sample Mining (AdaSaM) and Adaptive Outlier Filter (AdaOF). The first one gradually creates more reliable clusters to dynamically refine the memory, while the second can identify and filter out valuable outliers as negative samples.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
