Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qian, Xuelin, Lu, Jiaming, Wang, Zixuan, Wang, Wenxuan, Huang, Zhongling, Zhang, Dingwen, Han, Junwei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.20319
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914170813808640
author Qian, Xuelin
Lu, Jiaming
Wang, Zixuan
Wang, Wenxuan
Huang, Zhongling
Zhang, Dingwen
Han, Junwei
author_facet Qian, Xuelin
Lu, Jiaming
Wang, Zixuan
Wang, Wenxuan
Huang, Zhongling
Zhang, Dingwen
Han, Junwei
contents Infrared Small Target Detection (IRSTD) faces significant challenges due to low signal-to-noise ratios, complex backgrounds, and the absence of discernible target features. While deep learning-based encoder-decoder frameworks have advanced the field, their static pattern learning suffers from pattern drift across diverse scenarios (\emph{e.g.}, day/night variations, sky/maritime/ground domains), limiting robustness. To address this, we propose IrisNet, a novel meta-learned framework that dynamically adapts detection strategies to the input infrared image status. Our approach establishes a dynamic mapping between infrared image features and entire decoder parameters via an image-to-decoder transformer. More concretely, we represent the parameterized decoder as a structured 2D tensor preserving hierarchical layer correlations and enable the transformer to model inter-layer dependencies through self-attention while generating adaptive decoding patterns via cross-attention. To further enhance the perception ability of infrared images, we integrate high-frequency components to supplement target-position and scene-edge information. Experiments on NUDT-SIRST, NUAA-SIRST, and IRSTD-1K datasets demonstrate the superiority of our IrisNet, achieving state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20319
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IrisNet: Infrared Image Status Awareness Meta Decoder for Infrared Small Targets Detection
Qian, Xuelin
Lu, Jiaming
Wang, Zixuan
Wang, Wenxuan
Huang, Zhongling
Zhang, Dingwen
Han, Junwei
Computer Vision and Pattern Recognition
Infrared Small Target Detection (IRSTD) faces significant challenges due to low signal-to-noise ratios, complex backgrounds, and the absence of discernible target features. While deep learning-based encoder-decoder frameworks have advanced the field, their static pattern learning suffers from pattern drift across diverse scenarios (\emph{e.g.}, day/night variations, sky/maritime/ground domains), limiting robustness. To address this, we propose IrisNet, a novel meta-learned framework that dynamically adapts detection strategies to the input infrared image status. Our approach establishes a dynamic mapping between infrared image features and entire decoder parameters via an image-to-decoder transformer. More concretely, we represent the parameterized decoder as a structured 2D tensor preserving hierarchical layer correlations and enable the transformer to model inter-layer dependencies through self-attention while generating adaptive decoding patterns via cross-attention. To further enhance the perception ability of infrared images, we integrate high-frequency components to supplement target-position and scene-edge information. Experiments on NUDT-SIRST, NUAA-SIRST, and IRSTD-1K datasets demonstrate the superiority of our IrisNet, achieving state-of-the-art performance.
title IrisNet: Infrared Image Status Awareness Meta Decoder for Infrared Small Targets Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20319