SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization

Abstract

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.

arXiv commentAccepted at ECCV 2020 (https://link.springer.com/chapter/10.1007%2F978-3-030-58589-1_19) Code Available at https://github.com/ZhiHanZ/IRIS0-SPAN/

References in corpus (3)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
• Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)

Cited by in corpus (4)

• MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
• Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
• Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization
• TBFormer: Two-Branch Transformer for Image Forgery Localization