S$^2$Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915243951652864 |
|---|---|
| author | Lin, Yu Lin, Jianghang Ye, Kai Shen, You Zhang, Yan Zhang, Shengchuan Cao, Liujuan Ji, Rongrong |
| author_facet | Lin, Yu Lin, Jianghang Ye, Kai Shen, You Zhang, Yan Zhang, Shengchuan Cao, Liujuan Ji, Rongrong |
| contents | Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotation. Recent studies have explored weakly and semi-supervised learning to alleviate this burden. However, these methods overlook the difficulties posed by dense annotations in complex remote sensing scenes. In this paper, we introduce a novel setting called sparsely annotated oriented object detection (SAOOD), which only labels partial instances, and propose a solution to address its challenges. Specifically, we focus on two key issues in the setting: (1) sparse labeling leading to overfitting on limited foreground representations, and (2) unlabeled objects (false negatives) confusing feature learning. To this end, we propose the S$^2$Teacher, a novel method that progressively mines pseudo-labels for unlabeled objects, from easy to hard, to enhance foreground representations. Additionally, it reweights the loss of unlabeled objects to mitigate their impact during training. Extensive experiments demonstrate that S$^2$Teacher not only significantly improves detector performance across different sparse annotation levels but also achieves near-fully-supervised performance on the DOTA dataset with only 10% annotation instances, effectively balancing detection accuracy with annotation efficiency. The code will be public. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | S$^2$Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection Lin, Yu Lin, Jianghang Ye, Kai Shen, You Zhang, Yan Zhang, Shengchuan Cao, Liujuan Ji, Rongrong Computer Vision and Pattern Recognition Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotation. Recent studies have explored weakly and semi-supervised learning to alleviate this burden. However, these methods overlook the difficulties posed by dense annotations in complex remote sensing scenes. In this paper, we introduce a novel setting called sparsely annotated oriented object detection (SAOOD), which only labels partial instances, and propose a solution to address its challenges. Specifically, we focus on two key issues in the setting: (1) sparse labeling leading to overfitting on limited foreground representations, and (2) unlabeled objects (false negatives) confusing feature learning. To this end, we propose the S$^2$Teacher, a novel method that progressively mines pseudo-labels for unlabeled objects, from easy to hard, to enhance foreground representations. Additionally, it reweights the loss of unlabeled objects to mitigate their impact during training. Extensive experiments demonstrate that S$^2$Teacher not only significantly improves detector performance across different sparse annotation levels but also achieves near-fully-supervised performance on the DOTA dataset with only 10% annotation instances, effectively balancing detection accuracy with annotation efficiency. The code will be public. |
| title | S$^2$Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.11111 |