Linearly-evolved Transformer for Pan-sharpening

arXiv:2404.12804v1 Announce Type: new
Abstract: Vision transformer family has dominated the satellite pan-sharpening field driven by the global-wise spatial information modeling mechanism from the core self-attention ingredient. The standard modeling rules within these promising pan-sharpening methods are to roughly stack the transformer variants in a cascaded manner. Despite the remarkable advancement, their success may be at the huge cost of model parameters and FLOPs, thus preventing its application over low-resource satellites.To address this challenge between favorable performance and expensive computation, …

abstract advancement arxiv attention core cs.cv eess.iv family global information modeling rules satellite self-attention spatial stack standard success transformer type variants vision wise