通过语义与频域特征融合，提升伪装目标检测的边界精度。
SFGNet: Semantic and Frequency Guided Network for Camouflaged Object Detection
- 引入语义提示与频域模块捕捉伪装物体特征
- 在三个数据集上均超越现有最优方法
- 适合需要精细边界分割的视觉检测任务
伪装目标检测（COD）旨在分割与环境融为一体的物体。然而，现有研究多忽视不同目标文本提示的语义差异以及细粒度频域特征。本文提出一种新型语义与频域引导网络（SFGNet），结合语义提示与频域特征，以增强对伪装物体的感知和边界刻画能力。设计多带傅里叶模块（MBFM）提升复杂背景与模糊边界的处理能力，并引入交互式结构增强块（ISEB）确保预测结果的结构完整性和边界细节。在三个典型COD基准数据集上的大量实验表明，该方法显著优于当前最先进的方法。模型核心代码已开源：https://github.com/winter794444/SFGNetICASSP2026。
原文摘要 · Abstract (English)
Camouflaged object detection (COD) aims to segment objects that blend into their surroundings. However, most existing studies overlook the semantic differences among textual prompts of different targets as well as fine-grained frequency features. In this work, we propose a novel Semantic and Frequency Guided Network (SFGNet), which incorporates semantic prompts and frequency-domain features to capture camouflaged objects and improve boundary perception. We further design Multi-Band Fourier Module(MBFM) to enhance the ability of the network in handling complex backgrounds and blurred boundaries. In addition, we design an Interactive Structure Enhancement Block (ISEB) to ensure structural integrity and boundary details in the predictions. Extensive experiments conducted on three COD benchmark datasets demonstrate that our method significantly outperforms state-of-the-art approaches. The core code of the model is available at the following link: https://github.com/winter794444/SFGNetICASSP2026.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。