Key Laboratory of Aerospace Information Security and Trusted Computing (Ministry of Education),School of Cyber Science and Engineering,Wuhan University,Wuhan 430070,China.
To address the performance degradation and lack of robustness in existing forgery localization models when dealing with small region facial manipulations in multi-person scene images, a FMG-L model based on facial mask guidance for forgery localization is proposed. Firstly, to mitigate interference from background information in multi-person scene images, a facial mask guidance module is designed to encourage the model to focus on critical facial regions. Secondly, to enhance the robustness against image degradations, a three-channel feature extraction module is developed to extract multi-dimensional features, and a feature fusion module based on a dual attention network is also designed to enhance the forgery clues. Finally, a forgery localization module is used for forgery localization. Experimental results on the OpenForensics, ManulFake, FFIW, and DiffSwap datasets demonstrate that the FMG-L effectively localizes forgery regions and shows strong robustness against various image degradations and different online social platforms.
文献[20]中使用AUC(area under the ROC curve)作为定位性能的评估指标.然而,在多人场景图像中,篡改像素数量往往远小于真实像素数,导致严重的类别不平衡问题.在这种情况下,ROC曲线会偏向真实像素数,从而影响评估结果.因此,在本文的实验场景中,AUC评估可能给出不可信的结果.
2.4 参数设置
本文提出的伪造图像定位模型基于PyTorch实现,所有输入图像大小调整为,端到端的训练在2块NVIDIA Tesla V100 GPU上进行.本文使用Adamw[21]优化算法,初始学习率设置为,权重衰减系数设置为,设置最大训练周期.Focal loss中的损失权重.
WangT C, LiuM Y, ZhuJ Y, et al. High-resolution image synthesis and semantic manipulation with conditional gans[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 8798-8807.
[2]
DhariwalP, NicholA. Diffusion models beat gans on image synthesis[J]. Advances in Neural Information Processing Systems, 2021, 34: 8780-8794.
[3]
MirskyY, LeeW K. The creation and detection of deepfakes: a survey[J]. ACM Computing Surveys (CSUR), 2021, 54(1): 1-41.
[4]
LeT N, NguyenH H, YamagishiJ, et al. Openforensics: large-scale challenging dataset for multi-face forgery detection and segmentation in-the-wild[C]// IEEE/CVF International Conference on Computer Vision. Montreal, 2021: 10117-10127.
[5]
AgarwalA, RathaN. Deepfake Catcher: can a simple fusion be effective and outperform complex DNNs?[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, 2024: 3791-3801.
[6]
HeK M, GkioxariG, DollárP, et al. Mask r-CNN[C]// IEEE International Conference on Computer Vision. Venice, 2017: 2961-2969.
[7]
ZhouP, HanX T, MorariuV I, et al. Learning rich features for image manipulation detection[C]// IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 1053-1061.
[8]
FuJ, LiuJ, TianH J, et al. Dual attention network for scene segmentation[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, 2019: 3146-3154.
[9]
MaoA Q, MohriM, ZhongY T. Cross-entropy loss functions: theoretical analysis and applications[C]// The 40th International Conference on Machine Learning. Honolulu, 2023: 23803-23828.
[10]
RossT Y, DollárG. Focal loss for dense object detection[C]// IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017: 2980-2988.
[11]
KumarA, GuoY L, HuangX Y, et al. SeaBird: segmentation in bird's view with dice loss improves monocular 3D detection of large objects[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, 2024: 10269-10280.
[12]
WuH W, ZhouJ T, ZhangS L, et al. Exploring spatial-temporal features for deepfake detection and localization[EB/OL].(2022-10-28) [2024-08-13].
[13]
ZhouT F, WangW G, LiangZ Y, et al. Face forensics in the wild[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, 2021: 5778-5788.
[14]
ChenZ X, SunK, ZhouZ Y, et al. DiffusionFace: towards a comprehensive dataset for diffusion-based face forgery analysis[EB/OL]. (2024-03-27) [2024-08-13].
[15]
SelvarajuR R, CogswellM, DasA, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[EB/OL]. (2024-03-27) [2024-08-13].
[16]
CholletF. Xception: deep learning with depth wise separable convolutions[C]// IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017: 1251-1258.
[17]
ChaiL, BauD, LimS N, et al. What makes fake images detectable? understanding properties that generalize[C]// European Conference on Computer Vision. Glasgow, 2020: 103-120.
[18]
GuoX, LiuX H, RenZ Y, et al. Hierarchical fine-grained image forgery detection and localization[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, 2023: 3155-3165.
[19]
ȚânțaruD C, OneațăE, OneațăD. Weakly-supervised deepfake localization in diffusion-generated images[C]//IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa, 2024: 6258-6268.
[20]
HuangY H, XuJ F, WangR, et al. Fakelocator: robust localization of GAN-based face manipulations[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 2657-2672.
JiangL M, LiR, WuW, et al. Deeperforensics-1.0: a large-scale dataset for real-world face forgery detection[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, 2020: 2889-2898.