On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Shuo, Xing, Yinghui, Zhang, Shizhou, Niu, Zhilong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914144264912896
author Yang, Shuo
Xing, Yinghui
Zhang, Shizhou
Niu, Zhilong
author_facet Yang, Shuo
Xing, Yinghui
Zhang, Shizhou
Niu, Zhilong
contents Infrared and visible object detection (IVOD) is essential for numerous around-the-clock applications. Despite notable advancements, current IVOD models exhibit notable performance declines when confronted with incomplete modality data, particularly if the dominant modality is missing. In this paper, we take a thorough investigation on modality incomplete IVOD problem from an architecture compatibility perspective. Specifically, we propose a plug-and-play Scarf Neck module for DETR variants, which introduces a modality-agnostic deformable attention mechanism to enable the IVOD detector to flexibly adapt to any single or double modalities during training and inference. When training Scarf-DETR, we design a pseudo modality dropout strategy to fully utilize the multi-modality information, making the detector compatible and robust to both working modes of single and double modalities. Moreover, we introduce a comprehensive benchmark for the modality-incomplete IVOD task aimed at thoroughly assessing situations where the absent modality is either dominant or secondary. Our proposed Scarf-DETR not only performs excellently in missing modality scenarios but also achieves superior performances on the standard IVOD modality complete benchmarks. Our code will be available at https://github.com/YinghuiXing/Scarf-DETR.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective
Yang, Shuo
Xing, Yinghui
Zhang, Shizhou
Niu, Zhilong
Computer Vision and Pattern Recognition
Artificial Intelligence
Infrared and visible object detection (IVOD) is essential for numerous around-the-clock applications. Despite notable advancements, current IVOD models exhibit notable performance declines when confronted with incomplete modality data, particularly if the dominant modality is missing. In this paper, we take a thorough investigation on modality incomplete IVOD problem from an architecture compatibility perspective. Specifically, we propose a plug-and-play Scarf Neck module for DETR variants, which introduces a modality-agnostic deformable attention mechanism to enable the IVOD detector to flexibly adapt to any single or double modalities during training and inference. When training Scarf-DETR, we design a pseudo modality dropout strategy to fully utilize the multi-modality information, making the detector compatible and robust to both working modes of single and double modalities. Moreover, we introduce a comprehensive benchmark for the modality-incomplete IVOD task aimed at thoroughly assessing situations where the absent modality is either dominant or secondary. Our proposed Scarf-DETR not only performs excellently in missing modality scenarios but also achieves superior performances on the standard IVOD modality complete benchmarks. Our code will be available at https://github.com/YinghuiXing/Scarf-DETR.
title On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.06406