用多教师强化蒸馏，提升图像伪造检测与定位的效率和准确性。
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization
- 构建三个专精于不同伪造类型的教师模型，通过动态权重选择实现知识迁移。
- 在多个真实场景数据集上优于现有方法，显著提升对复杂伪造痕迹的识别能力。
- 适合需要高效、高精度伪造检测的安防与内容审核场景。
图像伪造检测与定位（IFDL）对于防止虚假信息传播至关重要。然而，现有方法难以应对真实场景中多样化的伪造操作。本文提出一种新型强化多教师知识蒸馏框架（Re-MTKD），基于编码器-解码器结构的Cue-Net模型，包含边缘感知模块。首先，分别训练三个针对复制-粘贴、拼接、修复三种主要伪造类型的专业教师模型；随后，利用自知识蒸馏方式指导目标学生模型学习。设计了强化动态教师选择策略（Re-DTS），动态分配教师权重，促进特定知识传递，使学生模型同时掌握各类篡改痕迹的共性与特性。大量实验表明，在多个新出现的伪造图像数据集上，该方法性能优于当前先进方法。
原文摘要 · Abstract (English)
Image forgery detection and localization (IFDL) is of vital importance as forged images can spread misinformation that poses potential threats to our daily lives. However, previous methods still struggled to effectively handle forged images processed with diverse forgery operations in real-world scenarios. In this paper, we propose a novel Reinforced Multi-teacher Knowledge Distillation (Re-MTKD) framework for the IFDL task, structured around an encoder-decoder \textbf{C}onvNeXt-\textbf{U}perNet along with \textbf{E}dge-Aware Module, named Cue-Net. First, three Cue-Net models are separately trained for the three main types of image forgeries, i.e., copy-move, splicing, and inpainting, which then serve as the multi-teacher models to train the target student model with Cue-Net through self-knowledge distillation. A Reinforced Dynamic Teacher Selection (Re-DTS) strategy is developed to dynamically assign weights to the involved teacher models, which facilitates specific knowledge transfer and enables the student model to effectively learn both the common and specific natures of diverse tampering traces. Extensive experiments demonstrate that, compared with other state-of-the-art methods, the proposed method achieves superior performance on several recently emerged datasets comprised of various kinds of image forgeries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。