Scholarlink

<p>Cross-domain few-annotation object detection (CFOD) faces significant challenges due to environmental variations and limited annotations in the target domain. This paper introduces a novel Memory Storage-to-Adaptation (MS2A) mechanism that leverages comprehensive prior knowledge from massive unlabeled data, representative of the target domain. The MS2A framework comprises two key components: a memory storage module for aggregating prior knowledge encompassing foreground object attributes and background context, and a memory adaptation module for integrating this memory into feature learning, resulting in discriminative representations. Experiments on both constructed and publicly available datasets demonstrate that MS2A achieves state-of-the-art performance, exceeding existing methods by up to 10.4% on challenging industrial datasets. Our code is available at: <a href="https://github.com/GuHuangAI/MS2A">https://github.com/GuHuangAI/MS2A</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

Enhancing cross-domain few-annotation object detection via memory storage-to-adaptation mechanism

  • 期刊论文

  • 发表日期：

    2026年6月17日

查看全文
  • Yuhang Huang,
  • Shilong Zou,
  • Ji Li,
  • Xuesong Xu,
  • Xiaohong Chen,
  • Xinwang Liu,
  • Kai Xu

摘要

Cross-domain few-annotation object detection (CFOD) faces significant challenges due to environmental variations and limited annotations in the target domain. This paper introduces a novel Memory Storage-to-Adaptation (MS2A) mechanism that leverages comprehensive prior knowledge from massive unlabeled data, representative of the target domain. The MS2A framework comprises two key components: a memory storage module for aggregating prior knowledge encompassing foreground object attributes and background context, and a memory adaptation module for integrating this memory into feature learning, resulting in discriminative representations. Experiments on both constructed and publicly available datasets demonstrate that MS2A achieves state-of-the-art performance, exceeding existing methods by up to 10.4% on challenging industrial datasets. Our code is available at: https://github.com/GuHuangAI/MS2A.