Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.18302 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918036731068416 |
|---|---|
| author | Shen, Gefei Sun, Yung-Hong Hu, Yu Hen Jiang, Hongrui |
| author_facet | Shen, Gefei Sun, Yung-Hong Hu, Yu Hen Jiang, Hongrui |
| contents | Two sampling strategies are investigated to enhance efficiency in training a deep learning object detection model. These sampling strategies are employed under the assumption of Lipschitz continuity of deep learning models. The first strategy is uniform sampling which seeks to obtain samples evenly yet randomly through the state space of the object dynamics. The second strategy of frame difference sampling is developed to explore the temporal redundancy among successive frames in a video. Experiment result indicates that these proposed sampling strategies provide a dataset that yields good training performance while requiring relatively few manually labelled samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18302 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sampling Strategies for Efficient Training of Deep Learning Object Detection Algorithms Shen, Gefei Sun, Yung-Hong Hu, Yu Hen Jiang, Hongrui Computer Vision and Pattern Recognition Information Theory Two sampling strategies are investigated to enhance efficiency in training a deep learning object detection model. These sampling strategies are employed under the assumption of Lipschitz continuity of deep learning models. The first strategy is uniform sampling which seeks to obtain samples evenly yet randomly through the state space of the object dynamics. The second strategy of frame difference sampling is developed to explore the temporal redundancy among successive frames in a video. Experiment result indicates that these proposed sampling strategies provide a dataset that yields good training performance while requiring relatively few manually labelled samples. |
| title | Sampling Strategies for Efficient Training of Deep Learning Object Detection Algorithms |
| topic | Computer Vision and Pattern Recognition Information Theory |
| url | https://arxiv.org/abs/2505.18302 |