Scholarlink

<p>Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. We propose a human–machine collaboration framework for COD, leveraging the complementary strengths of computer vision (CV) models and noninvasive brain-computer interfaces (BCIs). Our approach introduces a multiview backbone to estimate uncertainty in CV predictions, utilizes this uncertainty during training to improve efficiency, and defers low-confidence cases to human evaluation via RSVP-based BCIs during testing for more reliable decision-making. Evaluated on the CAMO dataset, our framework achieves state-of-the-art results with an average improvement of 4.56% in balanced accuracy (BA) and 3.66% in the F1 score. For the best-performing participants, improvements reached 7.6% in BA and 6.66% in the F1 score. Training analysis showed a strong correlation between confidence and precision, while ablation studies confirmed the effectiveness of our training policy and human–machine collaboration strategy. This work reduces human cognitive load, improves system reliability, and provides a foundation for advancements in real-world COD applications and human-computer interaction. Our code and data are available at: <a href="https://github.com/ziyuey/Uncertainty-aware-human-machine-collaboration-in-camouflaged-object-identification">https://github.com/ziyuey/Uncertainty-aware-human-machine-collaboration-in-camouflaged-object-identification</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

Uncertainty-aware human–machine collaboration in Camouflaged Object Detection

  • 期刊论文

  • 发表日期：

    2026年2月3日

查看全文
  • Ziyue Yang,
  • Kehan Wang,
  • Yuhang Ming,
  • Han Yang,
  • Qiong Chen,
  • Yong Peng,
  • Wanzeng Kong

摘要

Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. We propose a human–machine collaboration framework for COD, leveraging the complementary strengths of computer vision (CV) models and noninvasive brain-computer interfaces (BCIs). Our approach introduces a multiview backbone to estimate uncertainty in CV predictions, utilizes this uncertainty during training to improve efficiency, and defers low-confidence cases to human evaluation via RSVP-based BCIs during testing for more reliable decision-making. Evaluated on the CAMO dataset, our framework achieves state-of-the-art results with an average improvement of 4.56% in balanced accuracy (BA) and 3.66% in the F1 score. For the best-performing participants, improvements reached 7.6% in BA and 6.66% in the F1 score. Training analysis showed a strong correlation between confidence and precision, while ablation studies confirmed the effectiveness of our training policy and human–machine collaboration strategy. This work reduces human cognitive load, improves system reliability, and provides a foundation for advancements in real-world COD applications and human-computer interaction. Our code and data are available at: https://github.com/ziyuey/Uncertainty-aware-human-machine-collaboration-in-camouflaged-object-identification.