论文标题
跨度：空间金字塔注意网络的前进操纵定位
SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization
论文作者
论文摘要
我们提出了一个新颖的框架，即空间金字塔注意网络（SPAN），用于检测和定位多种类型的图像操作。提出的架构通过构造局部自我发场块的金字塔来有效有效地对多个尺度的图像斑块之间的关系进行建模。该设计包括一个新的位置投影，以编码斑块的空间位置。 SPAN是在通用，合成数据集上训练的，但也可以针对特定数据集进行微调。所提出的方法显示出在先前最新方法上的标准数据集上的性能上的显着提高。
We present a novel framework, Spatial Pyramid Attention Network (SPAN) for detection and localization of multiple types of image manipulations. The proposed architecture efficiently and effectively models the relationship between image patches at multiple scales by constructing a pyramid of local self-attention blocks. The design includes a novel position projection to encode the spatial positions of the patches. SPAN is trained on a generic, synthetic dataset but can also be fine tuned for specific datasets; The proposed method shows significant gains in performance on standard datasets over previous state-of-the-art methods.
