HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Harris, Vu, Tuan-Anh, Menon, Sanjith, Narasimhan, Sriram, Jawed, M. Khalid
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916947151552512
author Song, Harris
Vu, Tuan-Anh
Menon, Sanjith
Narasimhan, Sriram
Jawed, M. Khalid
author_facet Song, Harris
Vu, Tuan-Anh
Menon, Sanjith
Narasimhan, Sriram
Jawed, M. Khalid
contents Detecting hidden or partially concealed objects remains a fundamental challenge in multimodal environments, where factors like occlusion, camouflage, and lighting variations significantly hinder performance. Traditional RGB-based detection methods often fail under such adverse conditions, motivating the need for more robust, modality-agnostic approaches. In this work, we present HiddenObject, a fusion framework that integrates RGB, thermal, and depth data using a Mamba-based fusion mechanism. Our method captures complementary signals across modalities, enabling enhanced detection of obscured or camouflaged targets. Specifically, the proposed approach identifies modality-specific features and fuses them in a unified representation that generalizes well across challenging scenarios. We validate HiddenObject across multiple benchmark datasets, demonstrating state-of-the-art or competitive performance compared to existing methods. These results highlight the efficacy of our fusion design and expose key limitations in current unimodal and naïve fusion strategies. More broadly, our findings suggest that Mamba-based fusion architectures can significantly advance the field of multimodal object detection, especially under visually degraded or complex conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection
Song, Harris
Vu, Tuan-Anh
Menon, Sanjith
Narasimhan, Sriram
Jawed, M. Khalid
Computer Vision and Pattern Recognition
Artificial Intelligence
Detecting hidden or partially concealed objects remains a fundamental challenge in multimodal environments, where factors like occlusion, camouflage, and lighting variations significantly hinder performance. Traditional RGB-based detection methods often fail under such adverse conditions, motivating the need for more robust, modality-agnostic approaches. In this work, we present HiddenObject, a fusion framework that integrates RGB, thermal, and depth data using a Mamba-based fusion mechanism. Our method captures complementary signals across modalities, enabling enhanced detection of obscured or camouflaged targets. Specifically, the proposed approach identifies modality-specific features and fuses them in a unified representation that generalizes well across challenging scenarios. We validate HiddenObject across multiple benchmark datasets, demonstrating state-of-the-art or competitive performance compared to existing methods. These results highlight the efficacy of our fusion design and expose key limitations in current unimodal and naïve fusion strategies. More broadly, our findings suggest that Mamba-based fusion architectures can significantly advance the field of multimodal object detection, especially under visually degraded or complex conditions.
title HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.21135