IEEE Trans Image Process. 2021;30:2898-2907. doi: 10.1109/TIP.2021.3056212. Epub 2021 Feb 12.
In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing methods are primary to use pseudo labels to alleviate this problem. One of the most successful approaches predicts neighbors of each unlabeled image and then uses them to train the model. Although the predicted neighbors are credible, they always miss some hard positive samples, which may hinder the model from discovering important discriminative information of the unlabeled domain. In this paper, to complement these low recall neighbor pseudo labels, we propose a joint learning framework to learn better feature embeddings via high precision neighbor pseudo labels and high recall group pseudo labels. The group pseudo labels are generated by transitively merging neighbors of different samples into a group to achieve higher recall. However, the merging operation may cause subgroups in the group due to imperfect neighbor predictions. To utilize these group pseudo labels properly, we propose using a similarity-aggregating loss to mitigate the influence of these subgroups by pulling the input sample towards the most similar embeddings. Extensive experiments on three large-scale datasets demonstrate that our method can achieve state-of-the-art performance under the unsupervised domain adaptation re-ID setting.
近年来，监督式行人再识别（re-ID）模型受到了越来越多的研究。然而，这些在源域上训练的模型在测试于未见域时，性能总是会大幅下降。现有的方法主要使用伪标签来缓解这个问题。其中一种最成功的方法是预测每个未标记图像的邻居，然后使用它们来训练模型。虽然预测的邻居是可信的，但它们总是会错过一些硬正样本，这可能会阻碍模型发现未标记域的重要鉴别信息。在本文中，为了补充这些召回率低的邻居伪标签，我们提出了一个联合学习框架，通过高精度邻居伪标签和高召回率的组伪标签来学习更好的特征嵌入。组伪标签是通过将不同样本的邻居按序合并到一个组中来生成的，以实现更高的召回率。然而，合并操作可能会由于邻居预测不完美而导致组内产生子组。为了正确地利用这些组伪标签，我们提出使用相似性聚合损失来通过将输入样本向最相似的嵌入拉近，从而减轻这些子组的影响。在三个大规模数据集上的广泛实验表明，我们的方法在无监督域自适应 re-ID 设定下可以达到最新的性能。
