Feature Fusion and Knowledge-Distilled Multi-Modal Multi-Target Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Do, Ngoc Tuyen, Do, Tri Nhu
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