YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917646475198464 |
|---|---|
| author | Wan, Qian Xiang, Xiang Zhou, Qinhao |
| author_facet | Wan, Qian Xiang, Xiang Zhou, Qinhao |
| contents | Because of its use in practice, open-world object detection (OWOD) has gotten a lot of attention recently. The challenge is how can a model detect novel classes and then incrementally learn them without forgetting previously known classes. Previous approaches hinge on strongly-supervised or weakly-supervised novel-class data for novel-class detection, which may not apply to real applications. We construct a new benchmark that novel classes are only encountered at the inference stage. And we propose a new OWOD detector YOLOOC, based on the YOLO architecture yet for the Open-Class setup. We introduce label smoothing to prevent the detector from over-confidently mapping novel classes to known classes and to discover novel classes. Extensive experiments conducted on our more realistic setup demonstrate the effectiveness of our method for discovering novel classes in our new benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00257 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery Wan, Qian Xiang, Xiang Zhou, Qinhao Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing Because of its use in practice, open-world object detection (OWOD) has gotten a lot of attention recently. The challenge is how can a model detect novel classes and then incrementally learn them without forgetting previously known classes. Previous approaches hinge on strongly-supervised or weakly-supervised novel-class data for novel-class detection, which may not apply to real applications. We construct a new benchmark that novel classes are only encountered at the inference stage. And we propose a new OWOD detector YOLOOC, based on the YOLO architecture yet for the Open-Class setup. We introduce label smoothing to prevent the detector from over-confidently mapping novel classes to known classes and to discover novel classes. Extensive experiments conducted on our more realistic setup demonstrate the effectiveness of our method for discovering novel classes in our new benchmark. |
| title | YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2404.00257 |