SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters

• URL: http://arxiv.org/abs/2605.02258v1
• Date: Mon, 04 May 2026 06:09:13 GMT
• Title: SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters
• Abstract summary: Vision Foundation Models (VFMs) pretrained on large-scale RGB data have demonstrated remarkable representation quality.<n>Their applicability to multispectral imaging spanning Near-Infrared (NIR), Short-Wave Infrared (SWIR), and Long-Wave Infrared (LWIR) remains largely unexplored.<n>We present SpectraDINO, a multispectral VFM that bridges this spectral gap by extending DINOv2 ViT backbones to beyond-visible modalities.
• Score: 1.2622634782102324
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision Foundation Models (VFMs) pretrained on large-scale RGB data have demonstrated 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. We present SpectraDINO, a multispectral VFM that bridges this spectral gap by extending DINOv2 ViT backbones to beyond-visible modalities through lightweight, per-modality bottleneck adapters, while preserving the rich representations of the frozen RGB backbone. We introduce a multi-stage teacher-student training protocol in which a frozen DINOv2 teacher guides a spectral student via cosine distillation, symmetric contrastive loss, patch-level alignment, and a novel neighborhood-structure-preservation loss. This staged curriculum enables strong cross-modal alignment without catastrophic forgetting of RGB priors. We evaluate SpectraDINO on multispectral object detection and semantic segmentation across challenging NIR, SWIR, and LWIR benchmarks using widely adopted fusion strategies. SpectraDINO achieves state-of-the-art performance across most benchmarks, validating its effectiveness as a general-purpose backbone for spectral generalization. The code and weights for model variants are available at https://github.com/Yonsei-STL/SpectraDINO.

Related papers

• Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation [0.6187780920448871]
  We propose a multi-modal fusion architecture built upon dual ConvNeXt V2 backbones that employs stage-wise, modality-adaptive fusion strategies.<n>Experiments on MFNet and PST900 demonstrate that our lightest variant achieves 61.73% and 86.24% mIoU, respectively, with only 35.43M parameters.
  arXiv  Detail & Related papers  (2026-05-25T18:57:22Z)
• Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shifts [26.40090723572808]
  Domain Generalization Semantic (DGSS) in spectral remote sensing is severely challenged by spectral shifts across diverse acquisition conditions.<n>We propose SpectralMoE, a novel PEFT framework for DGSS that performs fine-grained, spatially-adaptive refinement of a foundation model's features.
  arXiv  Detail & Related papers  (2026-03-08T04:53:05Z)
• Spectral-Aware Global Fusion for RGB-Thermal Semantic Segmentation [10.761216101789774]
  We propose the Spectral-aware Global Fusion Network (SGFNet) to enhance and fuse the multi-modal features.<n>SGFNet outperforms the state-of-the-art methods on the MFNet and PST900 datasets.
  arXiv  Detail & Related papers  (2025-05-21T13:17:57Z)
• AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection [49.81255045696323]
  We present the Auxiliary Metadata Driven Infrared Small Target Detector (AuxDet)<n>AuxDet integrates metadata semantics with visual features, guiding adaptive representation learning for each sample.<n>Experiments on the challenging WideIRSTD-Full benchmark demonstrate that AuxDet consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-21T07:02:05Z)
• CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis [69.02751635551724]
  Spectral imaging offers promising applications across diverse domains, including medicine and urban scene understanding.<n> variability in channel dimensionality and captured wavelengths among spectral cameras impede the development of AI-driven methodologies.<n>We introduce CARL, a model for Camera-Agnostic Representation Learning across RGB, multispectral, and hyperspectral imaging modalities.
  arXiv  Detail & Related papers  (2025-04-27T13:06:40Z)
• Multi-Domain Biometric Recognition using Body Embeddings [51.36007967653781]
  We show that body embeddings perform better than face embeddings in medium-wave infrared (MWIR) and long-wave infrared (LWIR) domains.<n>We leverage a vision transformer architecture to establish benchmark results on the IJB-MDF dataset.<n>We also show that finetuning a body model, pretrained exclusively on VIS data, with a simple combination of cross-entropy and triplet losses achieves state-of-the-art mAP scores.
  arXiv  Detail & Related papers  (2025-03-13T22:38:18Z)
• Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection [67.02804741856512]
  We propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection.<n>Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions.
  arXiv  Detail & Related papers  (2025-01-25T06:21:06Z)
• Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution [54.293362972473595]
  Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Current approaches to address SR tasks are either dedicated to extracting RGB image features or assuming similar degradation patterns. We propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
  arXiv  Detail & Related papers  (2024-11-19T14:24:03Z)
• SpectralGPT: Spectral Remote Sensing Foundation Model [60.023956954916414]
  A universal RS foundation model, named SpectralGPT, is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT) Compared to existing foundation models, SpectralGPT accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS big data. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS big data applications within the field of geoscience.
  arXiv  Detail & Related papers  (2023-11-13T07:09:30Z)
• There and Back Again: Self-supervised Multispectral Correspondence Estimation [13.56924750612194]
  We introduce a novel cycle-consistency metric that allows us to self-supervise. This, combined with our spectra-agnostic loss functions, allows us to train the same network across multiple spectra. We demonstrate our approach on the challenging task of dense RGB-FIR correspondence estimation.
  arXiv  Detail & Related papers  (2021-03-19T12:33:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.