Our impression about one person often updates after we see more aspects of him/her and this process keeps iterating given more meetings. We formulate such an intuition into the problem of person re-identification (re-ID), where the representation of a query (probe) image is iteratively updated with new information from the candidates in the gallery. Specifically, we propose a simple attentional aggregation formulation to instantiate this idea and showcase that such a pipeline achieves competitive performance on standard benchmarks including CUHK03, Market-1501 and DukeMTMC. Not only does such a simple method improve the performance of the baseline models, it also achieves comparable performance with latest advanced re-ranking methods. Another advantage of this proposal is its flexibility to incorporate different representations and similarity metrics. By utilizing stronger representations and metrics, we further demonstrate state-of-the-art person re-ID performance, which also validates the general applicability of the proposed method.

中文翻译：

---

通过迭代印象聚合改进人员重新识别


当我们看到一个人的更多方面后，我们对他/她的印象通常会更新，并且随着会议次数的增加，这个过程会不断迭代。我们将这种直觉表述为人员重新识别（re-ID）问题，其中查询（探测）图像的表示会使用图库中候选者的新信息迭代更新。具体来说，我们提出了一个简单的注意力聚合公式来实例化这个想法，并展示这样的管道在包括 CUHK03、Market-1501 和 DukeMTMC 在内的标准基准上实现了具有竞争力的性能。这种简单的方法不仅提高了基线模型的性能，而且还实现了与最新的先进重排序方法相当的性能。该提案的另一个优点是它可以灵活地合并不同的表示和相似性度量。通过利用更强的表示和指标，我们进一步展示了最先进的行人重识别性能，这也验证了所提出方法的普遍适用性。