Scholarlink

<p>With the advancements in multimedia software and hardware technology, image forgery localization has become an important challenge in digital forensics. To improve the efficiency and stability of image forgery detection, we propose a mixed-domain perception and multi-expert decoding recognition model. First, we design an alignment strategy that utilizes both RGB and frequency domain information of images. This strategy adapts to the multi-dimensional distribution characteristics of the original data, enhancing the discrimination of tampered regions. Next, we employ a hybrid expert modeling approach to improve the model’s robustness in the representation space through feature selection and recombination. Additionally, we introduce a region-weighted contrastive learning method to better localize and focus on tampered regions. Experiments on four datasets (CASIA, NIST, COVERAGE, and IMD) show that our proposed model achieves an improvement in AUC ranging from 0.15 to 1.9% compared to the existing advanced methods. These results indicate that our approach contributes to more accurate image forgery localization, offering potential benefits for digital forensics and multimedia security applications.</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

Hybrid Domain Perception Combined With Multi-expert Decoding to Improve Image Forgery Localization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月8日

查看全文
  • Xuchao Gong,
  • Hongjie Duan,
  • Peiying Zhang,
  • Jian Wang,
  • Kai Liu,
  • Zhaohui Li

摘要

With the advancements in multimedia software and hardware technology, image forgery localization has become an important challenge in digital forensics. To improve the efficiency and stability of image forgery detection, we propose a mixed-domain perception and multi-expert decoding recognition model. First, we design an alignment strategy that utilizes both RGB and frequency domain information of images. This strategy adapts to the multi-dimensional distribution characteristics of the original data, enhancing the discrimination of tampered regions. Next, we employ a hybrid expert modeling approach to improve the model’s robustness in the representation space through feature selection and recombination. Additionally, we introduce a region-weighted contrastive learning method to better localize and focus on tampered regions. Experiments on four datasets (CASIA, NIST, COVERAGE, and IMD) show that our proposed model achieves an improvement in AUC ranging from 0.15 to 1.9% compared to the existing advanced methods. These results indicate that our approach contributes to more accurate image forgery localization, offering potential benefits for digital forensics and multimedia security applications.