Details

Autor(en) / Beteiligte

• Hu, Xuefeng
• Zhang, Zhihan
• Jiang, Zhenye
• Chaudhuri, Syomantak
• Yang, Zhenheng
• Nevatia, Ram
• Bischof, Horst
• Frahm, Jan-Michael
• Brox, Thomas
• Vedaldi, Andrea

Titel

SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization

Ist Teil von

• Computer Vision - ECCV 2020, 2020, Vol.12366, p.312-328

Ort / Verlag

Switzerland: Springer International Publishing AG

Erscheinungsjahr

2020

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• 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.