SpectraDINO extends DINOv2 with lightweight per-modality adapters and staged distillation to handle NIR, SWIR, and LWIR in one backbone, but its SWIR gain is weakened by using the evaluation dataset for pretraining.
arXiv preprint arXiv:2512.24561 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
CONDITIONAL 2roles
background 1polarities
background 1representative citing papers
OmniSch benchmarks large multimodal models on converting real PCB schematics into spatially weighted netlist graphs and finds large gaps in grounding, topology, and geometry.
citing papers explorer
-
SpectraDINO: Modality-Conditioned Adaptation of RGB Vision Foundation Models Across Infrared Bands
SpectraDINO extends DINOv2 with lightweight per-modality adapters and staged distillation to handle NIR, SWIR, and LWIR in one backbone, but its SWIR gain is weakened by using the evaluation dataset for pretraining.
-
OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning
OmniSch benchmarks large multimodal models on converting real PCB schematics into spatially weighted netlist graphs and finds large gaps in grounding, topology, and geometry.