Feature Fusion and Knowledge-Distilled Multi-Modal Multi-Target Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912405759459328 |
|---|---|
| author | Do, Ngoc Tuyen Do, Tri Nhu |
| author_facet | Do, Ngoc Tuyen Do, Tri Nhu |
| contents | In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed for resource-constrained embedded devices, particularly for Al-based solutions. To address these challenges, we propose a feature fusion and knowledge-distilled framework for multi-modal MTD that leverages data fusion to enhance accuracy and employs knowledge distillation for improved domain adaptation. Specifically, our approach utilizes both RGB and thermal image inputs within a novel fusion-based multi-modal model, coupled with a distillation training pipeline. We formulate the problem as a posterior probability optimization task, which is solved through a multi-stage training pipeline supported by a composite loss function. This loss function effectively transfers knowledge from a teacher model to a student model. Experimental results demonstrate that our student model achieves approximately 95% of the teacher model's mean Average Precision while reducing inference time by approximately 50%, underscoring its suitability for practical MTD deployment scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00365 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Feature Fusion and Knowledge-Distilled Multi-Modal Multi-Target Detection Do, Ngoc Tuyen Do, Tri Nhu Computer Vision and Pattern Recognition Signal Processing In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed for resource-constrained embedded devices, particularly for Al-based solutions. To address these challenges, we propose a feature fusion and knowledge-distilled framework for multi-modal MTD that leverages data fusion to enhance accuracy and employs knowledge distillation for improved domain adaptation. Specifically, our approach utilizes both RGB and thermal image inputs within a novel fusion-based multi-modal model, coupled with a distillation training pipeline. We formulate the problem as a posterior probability optimization task, which is solved through a multi-stage training pipeline supported by a composite loss function. This loss function effectively transfers knowledge from a teacher model to a student model. Experimental results demonstrate that our student model achieves approximately 95% of the teacher model's mean Average Precision while reducing inference time by approximately 50%, underscoring its suitability for practical MTD deployment scenarios. |
| title | Feature Fusion and Knowledge-Distilled Multi-Modal Multi-Target Detection |
| topic | Computer Vision and Pattern Recognition Signal Processing |
| url | https://arxiv.org/abs/2506.00365 |