A multiscale convolutional tokenizer plus MSM/PPP pretraining yields more accurate, parameter-efficient transformers for XRF pigment identification and unmixing than ViT, SpectralFormer, or 1D-CNN baselines.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing15, 3891–3903 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
XRFormer: Multiscale Tokenization for XRF Representation Learning
A multiscale convolutional tokenizer plus MSM/PPP pretraining yields more accurate, parameter-efficient transformers for XRF pigment identification and unmixing than ViT, SpectralFormer, or 1D-CNN baselines.