Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.20003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916967514898432 |
|---|---|
| author | Gautam, Somraj Purohit, Nachiketa Harit, Gaurav |
| author_facet | Gautam, Somraj Purohit, Nachiketa Harit, Gaurav |
| contents | Efficient data annotation remains a critical challenge in machine learning, particularly for object detection tasks requiring extensive labeled data. Active learning (AL) has emerged as a promising solution to minimize annotation costs by selecting the most informative samples. While traditional AL approaches primarily rely on uncertainty-based selection, recent advances suggest that incorporating diversity-based strategies can enhance sampling efficiency in object detection tasks. Our approach ensures the selection of representative examples that improve model generalization. We evaluate our method on two benchmark datasets (TableBank-LaTeX, TableBank-Word) using state-of-the-art table detection architectures, CascadeTabNet and YOLOv9. Our results demonstrate that AL-based example selection significantly outperforms random sampling, reducing annotation effort given a limited budget while maintaining comparable performance to fully supervised models. Our method achieves higher mAP scores within the same annotation budget. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Table Detection with Active Learning Gautam, Somraj Purohit, Nachiketa Harit, Gaurav Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Efficient data annotation remains a critical challenge in machine learning, particularly for object detection tasks requiring extensive labeled data. Active learning (AL) has emerged as a promising solution to minimize annotation costs by selecting the most informative samples. While traditional AL approaches primarily rely on uncertainty-based selection, recent advances suggest that incorporating diversity-based strategies can enhance sampling efficiency in object detection tasks. Our approach ensures the selection of representative examples that improve model generalization. We evaluate our method on two benchmark datasets (TableBank-LaTeX, TableBank-Word) using state-of-the-art table detection architectures, CascadeTabNet and YOLOv9. Our results demonstrate that AL-based example selection significantly outperforms random sampling, reducing annotation effort given a limited budget while maintaining comparable performance to fully supervised models. Our method achieves higher mAP scores within the same annotation budget. |
| title | Table Detection with Active Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.20003 |