Boost UAV-based Ojbect Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908171305484288 |
|---|---|
| author | Liu, Fan Yao, Liang Zhang, Chuanyi Wu, Ting Zhang, Xinlei Jiang, Xiruo Zhou, Jun |
| author_facet | Liu, Fan Yao, Liang Zhang, Chuanyi Wu, Ting Zhang, Xinlei Jiang, Xiruo Zhou, Jun |
| contents | Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three lightweight detection frameworks on two benchmark datasets. Extensive experiments demonstrate that our approach can effectively improve model accuracy and achieve state-of-the-art (SoTA) performance on two datasets. Our code and dataset will be publicly available once the paper is accepted. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_15465 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Boost UAV-based Ojbect Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning Liu, Fan Yao, Liang Zhang, Chuanyi Wu, Ting Zhang, Xinlei Jiang, Xiruo Zhou, Jun Computer Vision and Pattern Recognition Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three lightweight detection frameworks on two benchmark datasets. Extensive experiments demonstrate that our approach can effectively improve model accuracy and achieve state-of-the-art (SoTA) performance on two datasets. Our code and dataset will be publicly available once the paper is accepted. |
| title | Boost UAV-based Ojbect Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.15465 |