Do Pretrained Backbones Transfer to Physical Sensors? A Systematic Study of Multimodal Initialization Across the Sensor Stack
Transfer learning from pretrained backbones has become standard practice in multi-sensor computer vision---yet two questions remain open: which pretrained weights transfer best to multi-sensor setups, and can in-domain pretraining outperform off-the-shelf solutions?
By Fabio Montello, Ronja G\"uldenring, Lucas Mogensen Sandby, Christoffer Koo {\O}hrstr{\o}m, Lazaros NalpantidisarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 4, 2026.
Comments
Sign in to join the discussion.