Deep forgery detection method based on multi-granularity collaborative attention mechanism

Through the adaptive region division, dual-path feature separation and cross-grain size fusion of the multi-grain size synergistic attention mechanism, the problems of incomplete attention coverage, channel coupling interference and multi-scale information fusion in depth are solved, and high-precision and robust forgery detection are achieved.

CN120472547APending Publication Date: 2025-08-12XIDIAN UNIV
0 Cites 3 Cited by

Patent Information

Application Number
CN202510572091.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-30
Publication Date
2025-08-12

AI Technical Summary

Technical Problem

The existing deep forgery detection technology has problems such as incomplete spatial attention coverage, channel feature coupling interference and low synergistic efficiency of multi-grained features, resulting in reduced detection accuracy and insufficient generalization capabilities.

Method used

The multi-grained coordinated attention mechanism is adopted to achieve accurate capture and efficient discrimination of forged traces through dynamic spatial grouping, frequency domain decoupling and cross-grained size fusion, including adaptive region division, dual-path feature separation and cross-grained size feature interaction.

Benefits of technology

It significantly improves detection accuracy and generalization capabilities, enhances the model's adaptability and anti-interference ability to complex scenarios, and supports real-time processing and widespread application.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a deep forgery detection method based on a multi-granularity collaborative attention mechanism, and the method comprises the following steps: extracting multi-level features through a backbone network, achieving the self-adaptive region division and weight fusion through a dynamic space grouping attention mechanism, and solving the problem that a conventional method is insufficient in attention to a distributed forgery region; a double-path channel decoupling module is designed to separate high-frequency artifacts and low-frequency semantic features, and feature coupling interference is eliminated; a cross-granularity feature interaction network is constructed, local details and global semantic features are collaboratively optimized, and the fusion efficiency of multi-scale forged clues is improved; and finally, a detection result is output through the classifier. According to the method, the defects of weak cross-domain generalization ability, low multi-granularity information utilization efficiency and the like caused by incomplete space attention coverage and channel feature interference in the prior art are overcome, the detection precision and robustness are remarkably improved, the stable performance is kept in a complex degradation scene, and the method can be widely applied to scenes such as digital content security auditing and identity authentication.
Need to check novelty before this filing date? Find Prior Art