Scholarlink

<p>Camouflaged object detection (COD) aims to identify and segment camouflaged objects hidden in the environment. Previous methods based on CNN and Transformer still struggle to cope with more challenging scenes such as occlusions, rich edge detail and multiple objects. The performance of existing COD methods needs to be further improved. To address this issue, we have proposed a novel three-stage method, CAMFNet, for camouflaged object detection. The method uses PVTv2 as a backbone network and consists of three newly designed modules: (1) A multi-scale contextual feature enhancement (MCFE) module is designed to optimize the candidate features extracted by the Pvtv2 backbone network; (2) a multilevel interaction (MID) module is designed to generate coarse location information from the optimized candidate features; and (3) an adaptive feature fusion (AFF) module is designed to adaptively fuse the features from the encoder and decoder and achieve more accurate detection by using the position information provided by the MID. Ablation experiments show that the proposed three key modules are effective in improving the overall performance. Extensive experimental results on four benchmark COD datasets show that the CAMFNet outperforms 22 competitive methods. Our code is publicly available at <a href="https://github.com/Dp-zhou/CAMFNet">https://github.com/Dp-zhou/CAMFNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CAMFNet: complex camouflaged object detection via context-aware and adaptive multilevel feature fusion network

  • 期刊论文

  • 发表日期：

    2025年4月21日

查看全文
  • Bingqin Zhou,
  • Xionglong Li,
  • Miaoqing Li,
  • Kun Yang,
  • Wenyang Li,
  • Jing Xu

摘要

Camouflaged object detection (COD) aims to identify and segment camouflaged objects hidden in the environment. Previous methods based on CNN and Transformer still struggle to cope with more challenging scenes such as occlusions, rich edge detail and multiple objects. The performance of existing COD methods needs to be further improved. To address this issue, we have proposed a novel three-stage method, CAMFNet, for camouflaged object detection. The method uses PVTv2 as a backbone network and consists of three newly designed modules: (1) A multi-scale contextual feature enhancement (MCFE) module is designed to optimize the candidate features extracted by the Pvtv2 backbone network; (2) a multilevel interaction (MID) module is designed to generate coarse location information from the optimized candidate features; and (3) an adaptive feature fusion (AFF) module is designed to adaptively fuse the features from the encoder and decoder and achieve more accurate detection by using the position information provided by the MID. Ablation experiments show that the proposed three key modules are effective in improving the overall performance. Extensive experimental results on four benchmark COD datasets show that the CAMFNet outperforms 22 competitive methods. Our code is publicly available at https://github.com/Dp-zhou/CAMFNet.