Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.02861 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917828958879744 |
|---|---|
| author | Du, Bowei Liao, Zhixuan Zhang, Yanan Cai, Zhi Chen, Jiaxin Huang, Di |
| author_facet | Du, Bowei Liao, Zhixuan Zhang, Yanan Cai, Zhi Chen, Jiaxin Huang, Di |
| contents | Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is prohibitive for drones. Recently, Knowledge Distillation (KD) has shown promising potential for maintaining satisfactory accuracy while significantly compressing models in general object detection. Considering the advantages of KD, this paper presents the first attempt to adapt it to object detection on drone imagery and addresses two intrinsic issues: (1) low foreground-background ratio and (2) small instances and complex backgrounds, which lead to inadequate training, resulting insufficient distillation. Therefore, we propose a task-wise Lightweight Mutual Lifting (Light-ML) module with a Centerness-based Instance-aware Distillation (CID) strategy. The Light-ML module mutually harmonizes the classification and localization branches by channel shuffling and convolution, integrating teacher supervision across different tasks during back-propagation, thus facilitating training the student model. The CID strategy extracts valuable regions surrounding instances through the centerness of proposals, enhancing distillation efficacy. Experiments on the VisDrone, UAVDT, and COCO benchmarks demonstrate that the proposed approach promotes the accuracies of existing state-of-the-art KD methods with comparable computational requirements. Codes will be available upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02861 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery Du, Bowei Liao, Zhixuan Zhang, Yanan Cai, Zhi Chen, Jiaxin Huang, Di Computer Vision and Pattern Recognition Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is prohibitive for drones. Recently, Knowledge Distillation (KD) has shown promising potential for maintaining satisfactory accuracy while significantly compressing models in general object detection. Considering the advantages of KD, this paper presents the first attempt to adapt it to object detection on drone imagery and addresses two intrinsic issues: (1) low foreground-background ratio and (2) small instances and complex backgrounds, which lead to inadequate training, resulting insufficient distillation. Therefore, we propose a task-wise Lightweight Mutual Lifting (Light-ML) module with a Centerness-based Instance-aware Distillation (CID) strategy. The Light-ML module mutually harmonizes the classification and localization branches by channel shuffling and convolution, integrating teacher supervision across different tasks during back-propagation, thus facilitating training the student model. The CID strategy extracts valuable regions surrounding instances through the centerness of proposals, enhancing distillation efficacy. Experiments on the VisDrone, UAVDT, and COCO benchmarks demonstrate that the proposed approach promotes the accuracies of existing state-of-the-art KD methods with comparable computational requirements. Codes will be available upon acceptance. |
| title | Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.02861 |