Two-Stream Neural Networks for Tampered Face Detection

Authors: Peng Zhou, Xintong Han, Vlad I. Morariu, Larry S. Davis
Published: 2018-03-29

Source: https://arxiv.org/abs/1803.11276

PDF: https://arxiv.org/pdf/1803.11276

AIにより推定されたラベル

深層学習手法 ディープフェイクの検知 性能評価指標

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

We propose a two-stream network for face tampering detection. We train GoogLeNet to detect tampering artifacts in a face classification stream, and train a patch based triplet network to leverage features capturing local noise residuals and camera characteristics as a second stream. In addition, we use two different online face swapping applications to create a new dataset that consists of 2010 tampered images, each of which contains a tampered face. We evaluate the proposed two-stream network on our newly collected dataset. Experimental results demonstrate the effectiveness of our method.