{"ID":2844384,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06406","arxiv_id":"2511.06406","title":"On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.06406","url_pdf":"https://arxiv.org/pdf/2511.06406v1","authors":"[\"Shuo Yang\",\"Yinghui Xing\",\"Shizhou Zhang\",\"Zhilong Niu\"]","published":"2025-11-09T14:38:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":607288,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2844384,"paper_url":"https://arxiv.org/abs/2511.06406","paper_title":"On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective","repo_url":"https://github.com/YinghuiXing/Scarf-DETR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}