Label-Efficient Object Detection via Region Proposal Network Pre-Training
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917590375333888 |
|---|---|
| author | Dong, Nanqing Ericsson, Linus Yang, Yongxin Leonardis, Ales McDonagh, Steven |
| author_facet | Dong, Nanqing Ericsson, Linus Yang, Yongxin Leonardis, Ales McDonagh, Steven |
| contents | Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn transferable representations for downstream detection tasks. This leads to the necessity of training multiple detection-specific modules from scratch in the fine-tuning phase. We argue that the region proposal network (RPN), a common detection-specific module, can additionally be pre-trained towards reducing the localization error of multi-stage detectors. In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance. We evaluate the efficacy of our approach on benchmark object detection tasks and additional downstream tasks, including instance segmentation and few-shot detection. In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance, with largest gains found in label-scarce settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_09022 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Label-Efficient Object Detection via Region Proposal Network Pre-Training Dong, Nanqing Ericsson, Linus Yang, Yongxin Leonardis, Ales McDonagh, Steven Computer Vision and Pattern Recognition Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn transferable representations for downstream detection tasks. This leads to the necessity of training multiple detection-specific modules from scratch in the fine-tuning phase. We argue that the region proposal network (RPN), a common detection-specific module, can additionally be pre-trained towards reducing the localization error of multi-stage detectors. In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream object detection performance. We evaluate the efficacy of our approach on benchmark object detection tasks and additional downstream tasks, including instance segmentation and few-shot detection. In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance, with largest gains found in label-scarce settings. |
| title | Label-Efficient Object Detection via Region Proposal Network Pre-Training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2211.09022 |