Proactive Image Manipulation Detection

Vishal Asnani, Xi Yin, Tal Hassner, Sijia Liu, Xiaoming Liu

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء

ملخص

Image manipulation detection algorithms are often trained to discriminate between images manipulated with particular Generative Models (GMs) and genuine/real images, yet generalize poorly to images manipulated with GMs unseen in the training. Conventional detection algorithms receive an input image passively. By contrast, we propose a proactive scheme to image manipulation detection. Our key enabling technique is to estimate a set of templates which when added onto the real image would lead to more accurate manipulation detection. That is, a template protected real image, and its manipulated version, is better discriminated compared to the original real image vs. its manipulated one. These templates are estimated using certain constraints based on the desired properties of templates. For image manipulation detection, our proposed approach outperforms the prior work by an average precision of 16%for CycleGAN and 32% for GauGAN. Our approach is generalizable to a variety of GMs showing an improvement over prior work by an average precision of 10% averaged across 12 GMs. Our code is available at https://www.github.com/vishal3477/proactive_IMD.

اللغة الأصليةالإنجليزيّة
عنوان منشور المضيفProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
ناشرIEEE Computer Society
الصفحات15365-15374
عدد الصفحات10
رقم المعيار الدولي للكتب (الإلكتروني)9781665469463
المعرِّفات الرقمية للأشياء
حالة النشرنُشِر - 2022
الحدث2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, الولايات المتّحدة
المدة: ١٩ يونيو ٢٠٢٢٢٤ يونيو ٢٠٢٢

سلسلة المنشورات

الاسمProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
مستوى الصوت2022-June
رقم المعيار الدولي للدوريات (المطبوع)1063-6919

!!Conference

!!Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
الدولة/الإقليمالولايات المتّحدة
المدينةNew Orleans
المدة١٩/٠٦/٢٢٢٤/٠٦/٢٢

ملاحظة ببليوغرافية

Publisher Copyright:
© 2022 IEEE.

قم بذكر هذا