AI Paper Atlas

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

Residual-Guided Expert Specialization for Incomplete Multimodal Learning

Seunghun Baek, Jihwan Park, Jaeyoon Sim, Minjae Jeong, Hoseok Lee, Won Hwa Kim

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 1 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
add a mixture-of-experts structure (ablation)ResNet-18 · CASIA-SURFACER (%): 7.52 -> 4.12Improved
add residual routing (ablation)MoE · CASIA-SURFACER (%): 4.12 -> 3.78Improved
add noise regularization (ablation)MoE with residual routing · CASIA-SURFACER (%): 3.78 -> 2.72Improved
add discrepancy-guided sampling (ablation)MoE with residual routing and noise · CASIA-SURFACER (%): 2.72 -> 2.43Improved
add MoE (ablation)DeepLab v3+ · MCubeSmIoU: 0.4257 -> 0.4327Improved
add residual routing (ablation)MoE · MCubeSmIoU: 0.4327 -> 0.4661Improved
add noise regularization (ablation)MoE with residual routing · MCubeSmIoU: 0.4661 -> 0.4750Improved
add discrepancy-guided sampling (ablation)MoE with residual routing and noise · MCubeSmIoU: 0.4750 -> 0.4773Improved
use residual as router input instead of concatenation (ablation)MARS · CASIA-SURFACER (%): 3.83 -> 2.43Improved
use residual as router input instead of attention fusion (ablation)MARS · CASIA-SURFACER (%): 4.83 -> 2.43Improved
use residual as router input instead of ratio (ablation)MARS · CASIA-SURFACER (%): 12.01 -> 2.43Improved
feed true full-modality residuals at test time (oracle) (ablation)MARS · CASIA-SURFACER (%): 2.43 -> 0.94Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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