DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910641814503424 |
|---|---|
| author | Wang, Zhaoyong Liu, Yujie Li, Mingyue Zhang, Wenxin Li, Zongmin |
| author_facet | Wang, Zhaoyong Liu, Yujie Li, Mingyue Zhang, Wenxin Li, Zongmin |
| contents | In occluded person re-identification(ReID), severe occlusions lead to a significant amount of irrelevant information that hinders the accurate identification of individuals. These irrelevant cues primarily stem from background interference and occluding interference, adversely affecting the final retrieval results. Traditional discriminative models, which rely on the specific content and positions of the images, often misclassify in cases of occlusion. To address these limitations, we propose the Data Distribution Reconstruction Network (DDRN), a generative model that leverages data distribution to filter out irrelevant details, enhancing overall feature perception ability and reducing irrelevant feature interference. Additionally, severe occlusions lead to the complexity of the feature space. To effectively handle this, we design a multi-center approach through the proposed Hierarchical SubcenterArcface (HS-Arcface) loss function, which can better approximate complex feature spaces. On the Occluded-Duke dataset, we achieved a mAP of 62.4\% (+1.1\%) and a rank-1 accuracy of 71.3\% (+0.6\%), surpassing the latest state-of-the-art methods(FRT) significantly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06600 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification Wang, Zhaoyong Liu, Yujie Li, Mingyue Zhang, Wenxin Li, Zongmin Computer Vision and Pattern Recognition In occluded person re-identification(ReID), severe occlusions lead to a significant amount of irrelevant information that hinders the accurate identification of individuals. These irrelevant cues primarily stem from background interference and occluding interference, adversely affecting the final retrieval results. Traditional discriminative models, which rely on the specific content and positions of the images, often misclassify in cases of occlusion. To address these limitations, we propose the Data Distribution Reconstruction Network (DDRN), a generative model that leverages data distribution to filter out irrelevant details, enhancing overall feature perception ability and reducing irrelevant feature interference. Additionally, severe occlusions lead to the complexity of the feature space. To effectively handle this, we design a multi-center approach through the proposed Hierarchical SubcenterArcface (HS-Arcface) loss function, which can better approximate complex feature spaces. On the Occluded-Duke dataset, we achieved a mAP of 62.4\% (+1.1\%) and a rank-1 accuracy of 71.3\% (+0.6\%), surpassing the latest state-of-the-art methods(FRT) significantly. |
| title | DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.06600 |