← Back to all news
arXiv Computer Vision By Jeonghyeok Do, Munchurl Kim

SAREO-FM: Decoupled Semantic Supervision for SAR-EO Foundation Models

Read the original on arXiv Computer Vision →

SAREO‑FM is a foundation model that separates semantic supervision from reconstruction supervision in synthetic aperture radar (SAR) and electro‑optical (EO) imagery. It uses modality tokens for masked reconstruction and learnable semantic queries guided by a pretrained vision foundation model to capture scene content. Trained on the million‑scale SAR‑1M corpus, the model shows strong unimodal transfer for SAR and EO alone and significant improvements when both modalities are combined.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 7

Bridging Modalities and Tasks: A Unified Hierarchical ViT for SAR-to-Optical Translation and Semantic Segmentation

The paper introduces BMT, a unified hierarchical Vision Transformer that jointly performs SAR-to-optical image translation and semantic segmentation. It incorporates a LocalViTBlock, an enhanced output module, a ControlNet-style conditional injection, and a bounded Kendall uncertainty weighting scheme to balance the two tasks. Experiments on paired and unpaired datasets demonstrate competitive performance in both translation quality and segmentation accuracy.

By Siyuan Liu, Xuze Zhang, Yongshun Wang, Licong Pan, Hang Liu, Huihui Li
llmscomputer-visionsafety
More like this →
arXiv Machine Learning
Sep 10

Cross-modal learning for SAR target recognition using optical vision foundation models

The paper proposes a cross‑modal framework that uses a frozen DINOv3 optical vision foundation model to create class‑level prototypes for Synthetic Aperture Radar (SAR) target recognition. By aligning SAR embeddings to these optical prototypes, the SAR model learns to classify SAR images without needing paired optical data. Experiments on the UNICORNv2 dataset show that this prototype alignment improves SAR classification accuracy compared to baseline methods and yields clearer class separation in the embedding space.

By Lucas Hirsch, James R. Hopgood, Javid Khan, Yoann Altmann, Mike E. Davies
ragcomputer-visionfine-tuningmultimodalsafety
More like this →