M2SFormer, a Transformer encoder architecture with multi-spectral/multi-scale skip-connection attention and curvature-based difficulty guidance, achieves state-of-the-art cross-domain image forgery localization on several benchmarks.
Segnet: A deep convolutional encoder-decoder architecture for image segmentation.IEEE transactions on pattern anal- ysis and machine intelligence, 39(12):2481–2495, 2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization
M2SFormer, a Transformer encoder architecture with multi-spectral/multi-scale skip-connection attention and curvature-based difficulty guidance, achieves state-of-the-art cross-domain image forgery localization on several benchmarks.