Name
Abstract | ||
|---|---|---|
Most existing re-identification methods focus on learning ro-bust and discriminative features with deep convolution net-works. However, many of them consider content similarityseparately and fail to utilize the context information of thequery and gallery sets, e.g. probe-gallery and gallery-galleryrelations, thus hard samples may not be well solved due tothe limited or even misleading information. In this paper,we present a novel Context-Aware Graph Convolution Net-work (CAGCN), where the probe-gallery relations are en-coded into the graph nodes and the graph edge connectionsare well controlled by the gallery-gallery relations. In thisway, hard samples can be addressed with the context infor-mation flows among other easy samples during the graph rea-soning. Specifically, we adopt an effective hard gallery sam-pler to obtain high recall for positive samples while keeping areasonable graph size, which can also weaken the imbalancedproblem in training process with low computation complex-ity. Experiments show that the proposed method achievesstate-of-the-art performance on both person and vehicle re-identification datasets in a plug and play fashion with limitedoverhead. |
Year | Venue | DocType |
|---|---|---|
2021 | AAAI | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Deyi Ji | 1 | 0 | 1.01 |
| Haoran Wang | 2 | 0 | 0.34 |
| Hanzhe Hu | 3 | 2 | 2.43 |
| Weihao Gan | 4 | 34 | 5.40 |
| Wei Wu | 5 | 101 | 10.35 |
| Junjie Yan | 6 | 1288 | 58.19 |