AI RESEARCH
SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters
arXiv CS.CV
•
ArXi:2605.02258v1 Announce Type: new Vision Foundation Models (VFMs) pretrained on large-scale RGB data have nstrated remarkable representation quality, yet their applicability to multispectral imaging spanning Near-Infrared (NIR), Short-Wave Infrared (SWIR), and Long-Wave Infrared (LWIR) remains largely unexplored. These spectral modalities offer complementary sensing capabilities critical for robust perception in adverse conditions, but present a fundamental domain gap relative to RGB-centric pretrained models.