1. Improving Person Re-Identification With Iterative Impression Aggregation.
- Author
-
Fu, Dengpan, Xin, Bo, Wang, Jingdong, Chen, Dongdong, Bao, Jianmin, Hua, Gang, and Li, Houqiang
- Subjects
- *
PERFORMANCE standards , *TASK analysis , *INTUITION , *IDENTIFICATION - Abstract
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. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF