论文标题
是什么使假图像可以检测到？了解概括的属性
What makes fake images detectable? Understanding properties that generalize
论文作者
论文摘要
图像产生和操纵的质量达到了令人印象深刻的水平，使得人越来越难以区分真实和假货。但是，深层网络仍然可以掌握这些塑造的图像中微妙的文物。我们试图了解伪造图像的哪些属性使它们可以检测到它们，并确定在不同模型体系结构，数据集和培训中的变化之间的推广。我们使用具有有限接收场的基于补丁的分类器来可视化哪些假图像的区域更容易检测到。我们进一步展示了一种夸大这些可检测的属性的技术，并证明即使图像发生器针对伪造的图像分类器进行对抗，它仍然是不完美的，并且在某些图像贴片中留下可检测到的伪影。代码可在https://chail.github.io/patch-forensics/上找到。
The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle artifacts in these doctored images. We seek to understand what properties of fake images make them detectable and identify what generalizes across different model architectures, datasets, and variations in training. We use a patch-based classifier with limited receptive fields to visualize which regions of fake images are more easily detectable. We further show a technique to exaggerate these detectable properties and demonstrate that, even when the image generator is adversarially finetuned against a fake image classifier, it is still imperfect and leaves detectable artifacts in certain image patches. Code is available at https://chail.github.io/patch-forensics/.
