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.
Pad: Self-supervised pre-training with patchwise-scale adapter for infrared im- ages
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
UNIV introduces Patch Cross-modal Contrastive Learning (PCCL) to build a unified semantic feature space for infrared and visible modalities, supported by the new MVIP dataset of 98,992 aligned pairs, with reported gains on infrared segmentation and detection tasks.
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.
-
UNIV: Unified Foundation Model for Infrared and Visible Modalities
UNIV introduces Patch Cross-modal Contrastive Learning (PCCL) to build a unified semantic feature space for infrared and visible modalities, supported by the new MVIP dataset of 98,992 aligned pairs, with reported gains on infrared segmentation and detection tasks.