This letter focuses on image manipulation detection which aims to recognize the manipulated regions under the contextual semantic information. Existing approaches usually overlook the semantic discrepancy between different levels of feature maps, and directly fuse (e.g., addition, or concatenation) them for detection. In this letter, we argue that the semantic gap is the main reason for the low effectiveness of feature fusion in manipulation predictions. To address this problem, we propose a Global Semantic Consistency Network (GSCNet) for image manipulation detection, which is based on an encoder-decoder structure. Specifically, to make GSCNet include more global texture information which has been empirically confirmed to be beneficial to manipulation detection, gram block is first deployed on each level of feature maps in the encoding stage. Based on that, bi-directional convolutional LSTM is further implemented on the decoding stage, such that feature maps of the same level have semantic consistency. Experimental results on NIST16, and CASIA v1.0 declare that GSCNet can accurately locate the manipulated regions. Furthermore, compared to the existing models, GSCNet can achieve new state-of-the-art results.

中文翻译：

---

用于图像处理检测的全局语义一致性网络

这封信专注于图像操纵检测，旨在识别上下文语义信息下的操纵区域。现有方法通常忽略不同级别特征图之间的语义差异，并直接将它们融合（例如，添加或连接）以进行检测。在这封信中，我们认为语义差距是特征融合在操作预测中效率低下的主要原因。为了解决这个问题，我们提出了一种基于编码器-解码器结构的用于图像操作检测的全局语义一致性网络（GSCNet）。具体来说，为了让 GSCNet 包含更多的全局纹理信息，这些信息已被经验证实有利于操纵检测，首先在编码阶段在每一层特征图上部署 gram 块。在此基础上，在解码阶段进一步实现双向卷积LSTM，使得同一层的特征图具有语义一致性。NIST16 和 CASIA v1.0 上的实验结果表明 GSCNet 可以准确定位操纵区域。此外，与现有模型相比，GSCNet 可以实现新的最先进的结果。