Metraipolis › archive › dc_44dd97f9e247
DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection — arXiv:2609.00666
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00666
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:10:56.387Z
- SHA-256 of the archived text
40d525d9730292a757b7c31982c4feaf156a9973942d09ca7791a4322ce4b313- Stable URL of this page
https://metraipolis.com/documento/dc_44dd97f9e247
How to cite
DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection — arXiv:2609.00666 — arXiv (en), https://arxiv.org/abs/2609.00666 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44dd97f9e247 (Metraipolis archive dc_44dd97f9e247, sha256 40d525d9730292a757b7c31982c4feaf156a9973942d09ca7791a4322ce4b313)
BibTeX
@misc{dc44dd97f9e247,
title = {DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection — arXiv:2609.00666},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00666},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44dd97f9e247; sha256 40d525d9730292a757b7c31982c4feaf156a9973942d09ca7791a4322ce4b313},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00666. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
InfRared Small Target Detection (IRSTD) is a prominent and challenging task in computer vision. In recent years, text-guided methods have significantly improved detection performance. However, they still suffer from two key limitations. First, a single text description simultaneously modeling both background and target leads to semantic entanglement, which contradicts the objective of background suppression and target enhancement. Second, reliance on image-specific textual prompts (requiring additional external models such as CLIP during inference) results in deployment constraints. To address these issues, we propose a novel Dual-knowledge Guided Network (DGNet) based on multiple generalizable texts. Specifically, we design a Prior-knowledge Wavelet Modulation (PWM) module, which leverages dual textual priors that separately characterize large-scale backgrounds and sparse targets to effectively disentangle and modulate entangled semantics in the frequency domain. Furthermore, we introduce a Consensus-knowledge Directional Alignment (CDA) loss, which models the initial state and the ideal target across samples as `complex background' and `bright target', respectively, thereby constructing a clear and unified directional optimization trajectory for the model. Extensive experiments on three public datasets demonstrate the superior performance of DGNet and the effectiveness of each component. The source code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.00666 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:00:58.921Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).