AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SkySense-VITA: Towards Universal In-context Segmentation of Multi-modal Remote Sensing Imagery

Kang Wu, Lei Yu, Junwei Luo, Bo Dang, Junjian Zhang, Xiangyuan Cai, Hongwei Hu, Jingdong Chen, Yansheng Li

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add VITA-Former for prompt fusion (vs naive concat+conv fusion) (ablation)SkySense-VITA · FloodNetmIoU (fused): 47.96 -> 62.19Improved
add VITA-Former (ablation)SkySense-VITA · ETCI-FloodmIoU (fused): 20.26 -> 29.58Improved
add VITA-Former (ablation)SkySense-VITA · ETCI-FloodmIoU (visual-only): 27.63 -> 27.40No clear effect
add decoupled decoding (train visual, textual and fused branches jointly) (ablation)SkySense-VITA · FloodNetmIoU (textual-only): 34.57 -> 57.52Improved
add decoupled decoding (ablation)SkySense-VITA · FloodNetmIoU (fused): 59.31 -> 62.19Improved
add modality prototypes via cross-attention (ablation)VITA-Former · ETCI-FloodmIoU: 25.81 -> 29.58Improved
add modality prototypes by element-wise addition instead of cross-attention (ablation)VITA-Former · ETCI-FloodmIoU: 25.81 -> 14.39Hurt
add image-level optical-SAR alignment pretraining (ablation)SAR encoder · ETCI-FloodmIoU: 26.82 -> 29.58Improved
add image-level optical-SAR alignment pretraining (ablation)SAR encoder · C2S-SARmIoU: 13.68 -> 16.82Improved
add Semantic Granularity Annealing (coarse-to-fine curriculum) (ablation)pixel-level pretraining · iSAIDmIoU: 57.71 -> 59.89Improved
add Semantic Granularity Annealing (ablation)pixel-level pretraining · FloodNetmIoU: 61.03 -> 62.19Improved
use more precise visual prompt (point to box to mask) (ablation)SkySense-VITA visual-only · iSAIDmIoU: 23.97 -> 56.07Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy