Abstract | ||
---|---|---|
Cross-modality person re-identification is a challenging problem which retrieves a given pedestrian image in RGB modality among all the gallery images in infrared modality. The task can address the limitation of RGB-based person Re-ID in dark environments. Existing researches mainly focus on enlarging inter-class differences of feature to solve the problem. However, few studies investigate improving intra-class cross-modality similarity, which is important for this issue. In this paper, we propose a novel loss function, called Hetero-Center loss (HC loss) to reduce the intra-class cross-modality variations. Specifically, HC loss can supervise the network learning the cross-modality invariant information by constraining the intra-class center distance between two heterogenous modalities. With the joint supervision of Cross-Entropy (CE) loss and HC loss, the network is trained to achieve two vital objectives, inter-class discrepancy and intra-class cross-modality similarity as much as possible. Besides, we propose a simple and high-performance network architecture to learn local feature representations for cross-modality person re-identification, which can be a baseline for future research. Extensive experiments indicate the effectiveness of the proposed methods, which outperform state-of-the-art methods by a wide margin. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.neucom.2019.12.100 | Neurocomputing |
Keywords | DocType | Volume |
Cross-modality person re-identification,Hetero-Center loss,Local feature | Journal | 386 |
ISSN | Citations | PageRank |
0925-2312 | 5 | 0.50 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuanxin Zhu | 1 | 5 | 0.50 |
Yang Zhang | 2 | 164 | 21.65 |
Li Wang | 3 | 10 | 1.92 |
Sai Zhao | 4 | 5 | 0.50 |
Xiao Hu | 5 | 6 | 2.19 |
Dapeng Tao | 6 | 1115 | 61.57 |