Box-Level Class-Balanced Sampling for Active Object Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915461900271616 |
|---|---|
| author | Liao, Jingyi Xu, Xun Foo, Chuan-Sheng Cai, Lile |
| author_facet | Liao, Jingyi Xu, Xun Foo, Chuan-Sheng Cai, Lile |
| contents | Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most informative boxes to label and supplementing the sparsely-labelled image with pseudo labels, has been shown to be more cost-effective than selecting and labelling the entire image. In box-level AL for object detection, we observe that models at early stage can only perform well on majority classes, making the pseudo labels severely class-imbalanced. We propose a class-balanced sampling strategy to select more objects from minority classes for labelling, so as to make the final training data, \ie, ground truth labels obtained by AL and pseudo labels, more class-balanced to train a better model. We also propose a task-aware soft pseudo labelling strategy to increase the accuracy of pseudo labels. We evaluate our method on public benchmarking datasets and show that our method achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17849 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Box-Level Class-Balanced Sampling for Active Object Detection Liao, Jingyi Xu, Xun Foo, Chuan-Sheng Cai, Lile Computer Vision and Pattern Recognition Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most informative boxes to label and supplementing the sparsely-labelled image with pseudo labels, has been shown to be more cost-effective than selecting and labelling the entire image. In box-level AL for object detection, we observe that models at early stage can only perform well on majority classes, making the pseudo labels severely class-imbalanced. We propose a class-balanced sampling strategy to select more objects from minority classes for labelling, so as to make the final training data, \ie, ground truth labels obtained by AL and pseudo labels, more class-balanced to train a better model. We also propose a task-aware soft pseudo labelling strategy to increase the accuracy of pseudo labels. We evaluate our method on public benchmarking datasets and show that our method achieves state-of-the-art performance. |
| title | Box-Level Class-Balanced Sampling for Active Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.17849 |