Abstract | ||
---|---|---|
AbstractAbstractExtracting discriminative pedestrian features is an effective method in person re-identification. Most person re-identification works focus on extracting abstract features from the high-layer of the network, but ignore the middle-layer features, thus reducing the identity accuracy. To solve this problem, we construct a Smooth Aggregation Module (SAM) to extract, align, and fuse the feature maps in the middle-layer of the network to make up for the lack of detailed information in the high-level network features, and propose an Omni-Scale Feature Aggregation method (OSFA) Source codes are available at https://github.com/lyy973/OSFA.git. to jointly learn the abstract features and local detail features. Considering that the intra-class distance in person re-identification should be less than the inter-class distance, we combine multiple losses to constrain the model. We evaluate the performance of our method on three standard benchmark datasets: Market-1501, CUHK03 (both detected and labeled) and DukeMTMC-reID, and experimental results show that our method is superior to the state-of-the-art approaches. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.knosys.2021.107281 | Periodicals |
Keywords | DocType | Volume |
Person re-identification, Multi-scale, Representation learning, Feature fusion | Journal | 228 |
Issue | ISSN | Citations |
C | 0950-7051 | 1 |
PageRank | References | Authors |
0.35 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yueying Li | 1 | 1 | 0.35 |
Li Liu | 2 | 169 | 50.09 |
Lei Zhu | 3 | 854 | 51.69 |
Huaxiang Zhang | 4 | 436 | 56.32 |