AI Paper Atlas

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

Robust Multimodal Learning With Missing Modalities via Parameter-Efficient Adaptation

Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif

TPAMI 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 82 citations (OpenAlex)

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
adapt with scale and shift layers for the missing-modality caseCMNeXt (Thermal only) · MFNetmIoU (%): 35.48 -> 50.89Improved
adapt with scale and shift layers for the missing-modality caseCMNeXt (Depth only) · NYUDv2mIoU (%): 5.26 -> 36.72Improved
adapt with scale and shift layers for the missing-modality caseCMNeXt (RGB only) · MCubeSmIoU (%): 42.32 -> 50.43Improved
replace modality duplication with adaptationCMNeXt (RGB only) · NYUDv2mIoU (%): 46.19 -> 52.82Improved
use adapted shared model instead of dedicated per-combination modelsCMNeXt (Thermal only) · MFNetmIoU (%): 53.34 -> 50.89Mixed
add shift parameters to scale-only adaptation (ablation)scale-and-shift adaptation · MFNet (avg)mIoU (%): 52.00 -> 53.06Improved
add scale parameters to shift-only adaptation (ablation)scale-and-shift adaptation · MFNet (avg)mIoU (%): 51.77 -> 53.06Improved
use scale and shift instead of LoRA (ablation)parameter-efficient adaptation · MFNet (avg)mIoU (%): 50.82 -> 53.06Improved
use scale and shift instead of BitFit (ablation)parameter-efficient adaptation · MFNet (avg)mIoU (%): 51.73 -> 53.06Improved
use scale and shift instead of BitFit (ablation)parameter-efficient adaptation · NYUDv2 (avg)mIoU (%): 44.87 -> 44.77No clear effect
use scale and shift instead of normalization-layer fine-tuning (ablation)parameter-efficient adaptation · MFNet (avg)mIoU (%): 51.07 -> 53.06Improved
replace input prompts with scale-and-shift adaptationViLT · UPMC Food-101accuracy (%): 78.54 -> 79.83Improved

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