Saved in:
Bibliographic Details
Main Authors: Kim, Taeheon, Chung, Sangyun, Yeom, Damin, Yu, Youngjoon, Kim, Hak Gu, Ro, Yong Man
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.15209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929664283377664
author Kim, Taeheon
Chung, Sangyun
Yeom, Damin
Yu, Youngjoon
Kim, Hak Gu
Ro, Yong Man
author_facet Kim, Taeheon
Chung, Sangyun
Yeom, Damin
Yu, Youngjoon
Kim, Hak Gu
Ro, Yong Man
contents Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in certain cases (e.g., thermal-obscured pedestrians), particularly due to the modality bias learned from statistically biased datasets. In this paper, we investigate how to mitigate modality bias in multispectral pedestrian detection using Large Language Models (LLMs). Accordingly, we design a Multispectral Chain-of-Thought (MSCoT) prompting strategy, which prompts the LLM to perform multispectral pedestrian detection. Moreover, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework that integrates MSCoT prompting into multispectral pedestrian detection. To this end, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing the outputs of MSCoT prompting with the detection results of vision-based multispectral pedestrian detection models. Extensive experiments validate that MSCoTDet effectively mitigates modality biases and improves multispectral pedestrian detection.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15209
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection
Kim, Taeheon
Chung, Sangyun
Yeom, Damin
Yu, Youngjoon
Kim, Hak Gu
Ro, Yong Man
Computer Vision and Pattern Recognition
Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in certain cases (e.g., thermal-obscured pedestrians), particularly due to the modality bias learned from statistically biased datasets. In this paper, we investigate how to mitigate modality bias in multispectral pedestrian detection using Large Language Models (LLMs). Accordingly, we design a Multispectral Chain-of-Thought (MSCoT) prompting strategy, which prompts the LLM to perform multispectral pedestrian detection. Moreover, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework that integrates MSCoT prompting into multispectral pedestrian detection. To this end, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing the outputs of MSCoT prompting with the detection results of vision-based multispectral pedestrian detection models. Extensive experiments validate that MSCoTDet effectively mitigates modality biases and improves multispectral pedestrian detection.
title MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.15209