Enhancing Long-Term Re-Identification Robustness Using Synthetic Data: A Comparative Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915258604453888 |
|---|---|
| author | Pionzewski, Christian Rademacher, Rebecca Rutinowski, Jérôme Ponikarov, Antonia Matzke, Stephan Chilla, Tim Schreynemackers, Pia Kirchheim, Alice |
| author_facet | Pionzewski, Christian Rademacher, Rebecca Rutinowski, Jérôme Ponikarov, Antonia Matzke, Stephan Chilla, Tim Schreynemackers, Pia Kirchheim, Alice |
| contents | This contribution explores the impact of synthetic training data usage and the prediction of material wear and aging in the context of re-identification. Different experimental setups and gallery set expanding strategies are tested, analyzing their impact on performance over time for aging re-identification subjects. Using a continuously updating gallery, we were able to increase our mean Rank-1 accuracy by 24%, as material aging was taken into account step by step. In addition, using models trained with 10% artificial training data, Rank-1 accuracy could be increased by up to 13%, in comparison to a model trained on only real-world data, significantly boosting generalized performance on hold-out data. Finally, this work introduces a novel, open-source re-identification dataset, pallet-block-2696. This dataset contains 2,696 images of Euro pallets, taken over a period of 4 months. During this time, natural aging processes occurred and some of the pallets were damaged during their usage. These wear and tear processes significantly changed the appearance of the pallets, providing a dataset that can be used to generate synthetically aged pallets or other wooden materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Long-Term Re-Identification Robustness Using Synthetic Data: A Comparative Analysis Pionzewski, Christian Rademacher, Rebecca Rutinowski, Jérôme Ponikarov, Antonia Matzke, Stephan Chilla, Tim Schreynemackers, Pia Kirchheim, Alice Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.10; I.4.9 This contribution explores the impact of synthetic training data usage and the prediction of material wear and aging in the context of re-identification. Different experimental setups and gallery set expanding strategies are tested, analyzing their impact on performance over time for aging re-identification subjects. Using a continuously updating gallery, we were able to increase our mean Rank-1 accuracy by 24%, as material aging was taken into account step by step. In addition, using models trained with 10% artificial training data, Rank-1 accuracy could be increased by up to 13%, in comparison to a model trained on only real-world data, significantly boosting generalized performance on hold-out data. Finally, this work introduces a novel, open-source re-identification dataset, pallet-block-2696. This dataset contains 2,696 images of Euro pallets, taken over a period of 4 months. During this time, natural aging processes occurred and some of the pallets were damaged during their usage. These wear and tear processes significantly changed the appearance of the pallets, providing a dataset that can be used to generate synthetically aged pallets or other wooden materials. |
| title | Enhancing Long-Term Re-Identification Robustness Using Synthetic Data: A Comparative Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.10; I.4.9 |
| url | https://arxiv.org/abs/2504.18286 |