分类 - IML
Employing_Reinforcement_Learning_to_Construct_a_Decision-Making_Environment_for_Image_Forgery_Localization
Employing_Reinforcement_Learning_to_Construct_a_Decision-Making_Environment_for_Image_Forgery_Localization

发表于TIFS2024,将强化学习引入到了图像篡改检测。

11
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization

发表于AAAI2025,该框架的核心是Re-DTS策略,动态选择最合适的教师模型,将专业知识转移到学生模型。这一策略增强了学生模型处理各种篡改痕迹的能力,并提高了IFDL性能,将强化学习引入到了图像篡改检测。

12
Rethinking Image Editing Detection in the Era of Generative AI Revolution
Rethinking Image Editing Detection in the Era of Generative AI Revolution

发表于ACMMM 2025,提出了基于图像编辑技术的新数据集。

13
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

发表于TIP 2024,图像复制-移动伪造检测方向的图像篡改检测方法。

14
DiRLoc:Disentanglement Representation Learning for Robust Image Forgery Localization
DiRLoc:Disentanglement Representation Learning for Robust Image Forgery Localization

发表于TDSC2024,针对JPEG压缩导致的性能下降,使用解纠缠的方法,分离出jpeg压缩对篡改痕迹的影响,提出了一种鲁棒的图像伪造定位框架。

15
IMDL-BenCo:A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
IMDL-BenCo:A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization

发表于NeurIPS 2024,因为图像篡改检测没有统一的标准,所以构建一个全面的基准,并且设计了一个框架将部分sota网络集成:Mantra-Net,MVSS-net,CAT-Net,ObjectFormer,PSCC-Net,NCL-IML,Trufor和IML-ViT。

16
SparseViT:Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer
SparseViT:Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer

发表于AAAI2025,SparseViT认为图像篡改检测应该是非语义的,非语义特征与上下文无关,且对篡改敏感。也就是说,在图像中,除非发生篡改,否则它们在各个补丁之间是一致的,而图像块之间的稀疏和离散交互足以提取非语义特征,非语义特征由于其局部独立性,可以通过稀疏编码实现全局交互。

17
DiffForensics:Leveraging Diffusion Prior to Image Forgery Detection and Localization
DiffForensics:Leveraging Diffusion Prior to Image Forgery Detection and Localization

发表于CVPR2024,两阶段的训练过程,该框架包括自监督去噪扩散的训练前阶段和多任务微调阶段,提出了一种新的边缘提示增强模块,该模块集成在多个尺度的解码器中,以增强被篡改的边缘痕迹从粗到细。

18
SUMI-IFL:An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints
SUMI-IFL:An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints

发表于aixiv,使用信息瓶颈理论完成图像篡改任务,没和NP++、IFL-VIT比较。

19
EditGuard:Versatile Image Watermarking for Tamper Localization and Copyright Protection
EditGuard:Versatile Image Watermarking for Tamper Localization and Copyright Protection

发表于CVPR2024,将版权水印和图像篡改主动保护两个任务联合起来。

20