CBC-SLP structures latent representations into shared and modality-specific components with adaptive transfer to the decoder, outperforming prior multimodal segmentation models under both full and missing modality conditions while recovering complementary information.
Cfformer: A cross-fusion transformer framework for the semantic seg- mentation of multi-source remote sensing images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Multispectral Semantic Segmentation under Missing or Full Modalities via Structured Latent Projection
CBC-SLP structures latent representations into shared and modality-specific components with adaptive transfer to the decoder, outperforming prior multimodal segmentation models under both full and missing modality conditions while recovering complementary information.