SPIRIT: Adapting Vision Foundation Models for Unified Single- and Multi-Frame Infrared Small Target Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Qian, Li, Xi, Gao, Fei, Guo, Jie, Yuan, Haojuan, Fan, Shuaipeng, Zhang, Mingjin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917241568624640
author Xu, Qian
Li, Xi
Gao, Fei
Guo, Jie
Yuan, Haojuan
Fan, Shuaipeng
Zhang, Mingjin
author_facet Xu, Qian
Li, Xi
Gao, Fei
Guo, Jie
Yuan, Haojuan
Fan, Shuaipeng
Zhang, Mingjin
contents Infrared small target detection (IRSTD) is crucial for surveillance and early-warning, with deployments spanning both single-frame analysis and video-mode tracking. A practical solution should leverage vision foundation models (VFMs) to mitigate infrared data scarcity, while adopting a memory-attention-based temporal propagation framework that unifies single- and multi-frame inference. However, infrared small targets exhibit weak radiometric signals and limited semantic cues, which differ markedly from visible-spectrum imagery. This modality gap makes direct use of semantics-oriented VFMs and appearance-driven cross-frame association unreliable for IRSTD: hierarchical feature aggregation can submerge localized target peaks, and appearance-only memory attention becomes ambiguous, leading to spurious clutter associations. To address these challenges, we propose SPIRIT, a unified and VFM-compatible framework that adapts VFMs to IRSTD via lightweight physics-informed plug-ins. Spatially, PIFR refines features by approximating rank-sparsity decomposition to suppress structured background components and enhance sparse target-like signals. Temporally, PGMA injects history-derived soft spatial priors into memory cross-attention to constrain cross-frame association, enabling robust video detection while naturally reverting to single-frame inference when temporal context is absent. Experiments on multiple IRSTD benchmarks show consistent gains over VFM-based baselines and SOTA performance.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01843
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SPIRIT: Adapting Vision Foundation Models for Unified Single- and Multi-Frame Infrared Small Target Detection
Xu, Qian
Li, Xi
Gao, Fei
Guo, Jie
Yuan, Haojuan
Fan, Shuaipeng
Zhang, Mingjin
Computer Vision and Pattern Recognition
Infrared small target detection (IRSTD) is crucial for surveillance and early-warning, with deployments spanning both single-frame analysis and video-mode tracking. A practical solution should leverage vision foundation models (VFMs) to mitigate infrared data scarcity, while adopting a memory-attention-based temporal propagation framework that unifies single- and multi-frame inference. However, infrared small targets exhibit weak radiometric signals and limited semantic cues, which differ markedly from visible-spectrum imagery. This modality gap makes direct use of semantics-oriented VFMs and appearance-driven cross-frame association unreliable for IRSTD: hierarchical feature aggregation can submerge localized target peaks, and appearance-only memory attention becomes ambiguous, leading to spurious clutter associations. To address these challenges, we propose SPIRIT, a unified and VFM-compatible framework that adapts VFMs to IRSTD via lightweight physics-informed plug-ins. Spatially, PIFR refines features by approximating rank-sparsity decomposition to suppress structured background components and enhance sparse target-like signals. Temporally, PGMA injects history-derived soft spatial priors into memory cross-attention to constrain cross-frame association, enabling robust video detection while naturally reverting to single-frame inference when temporal context is absent. Experiments on multiple IRSTD benchmarks show consistent gains over VFM-based baselines and SOTA performance.
title SPIRIT: Adapting Vision Foundation Models for Unified Single- and Multi-Frame Infrared Small Target Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.01843