AI Paper Atlas

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

Decoupled and Reusable Adaptation for Efficient Cross-Modal Transfer

Yajing Liu, Yumeng Zhang, Yue Si, Baojie Fan, Jiandong Tian

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer

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 Stage 1 Progressive Self-Supervised Tuning (modality LoRA) (ablation)TP-MoME with SAM 2 Hiera-B+ · MCubeS and DELIVER (average)Avg mIoU (%): 54.9 -> 59.3Improved
add MAE training in Stage 1 (ablation)TP-MoME · MCubeS and DELIVER (average)Avg mIoU (%): 54.9 -> 56.2Improved
add DINOv2-style training in Stage 1 (ablation)TP-MoME · MCubeS and DELIVER (average)Avg mIoU (%): 54.9 -> 57.1Improved
combine MAE and DINOv2 trained independently (ablation)TP-MoME · MCubeS and DELIVER (average)Avg mIoU (%): 54.9 -> 58.2Improved
use MAE warm-up then MAE-guided consistency learning instead of independent training (ablation)PSST · MCubeS and DELIVER (average)Avg mIoU (%): 58.2 -> 59.3Improved
use MoME instead of simple gated summation for fusion (ablation)TP-MoME · MCubeS and DELIVER (average)Avg mIoU (%): 58.1 -> 59.3Improved
use MoME instead of gated summation with more modalities (RGB-A-D) (ablation)TP-MoME · MCubeS (RGB-A-D)mIoU (%): 52.7 -> 54.4Improved
use MoME instead of gated summation with more modalities (RGB-D-E) (ablation)TP-MoME · DELIVER (RGB-Depth-Event)mIoU (%): 63.6 -> 65.1Improved
decoupled modality LoRA plus task adaptation versus MemorySAM on trainable parametersOurs · Five downstream tasks (storage)Accumulated parameters (M): 153.7 -> 121.4Improved
add Stage 1 modality knowledge, label efficiencyOurs · MCubeSmIoUImproved
add Stage 1 modality knowledge, training speed (ablation)Ours · MCubeStraining epochs: epoch 5 vs MemorySAM epoch 12Improved
Ours (Hiera-B+) versus full fine-tuned CMNeXt on RGB-T MFNetOurs · MFNet (RGB-T)mIoU (%): 59.9 -> 60.5Improved

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