AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective

Kaifang Long, Lianbo Ma, Jiaqi Liu, Liming Liu, Guoyang Xie

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 2 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 Mamba decoder (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 6-1 with 4 stepsI-AUROC: 75.3 -> 76.0Improved
add IBFM (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 6-1 with 4 stepsI-AUROC: 75.3 -> 76.9Improved
add both Mamba decoder and IBFM (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 6-1 with 4 stepsI-AUROC: 75.3 -> 78.6Improved
add both Mamba decoder and IBFM (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 6-1 with 4 stepsforgetting metric: 12.7 -> 9.3Improved
add both Mamba decoder and IBFM (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 9-1 with 1 stepI-AUROC: 85.1 -> 87.5Improved
add both Mamba decoder and IBFM (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 10-0 with 0 stepI-AUROC: 86.7 -> 91.0Improved
use cross-attention fusion instead of addition (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 10-0 with 0 stepI-AUROC: 89.8 -> 91.0Improved
use cross-attention fusion instead of LinearGLU (ablation)IB-IUMAD · MVTec 3D-AD RGB+3D, 10-0 with 0 stepI-AUROC: 86.7 -> 91.0Improved
IB-IUMAD vs IUF in 6-1 with 4 steps (RGB+3D)IUF · MVTec 3D-AD RGB+3D, 6-1 with 4 stepsI-AUROC: 75.1 -> 78.6Improved
IB-IUMAD vs CDAD in 9-1 with 1 step (RGB)CDAD · MVTec 3D-AD RGB, 9-1 with 1 stepI-AUROC: 74.2 -> 85.3Improved
IB-IUMAD vs CDAD on Eyecandies 3D forgetting, 9-1 with 1 stepCDAD · Eyecandies 3D, 9-1 with 1 stepforgetting metric: 0.9 / 0.1 -> 1.4 / 1.3Hurt
IB-IUMAD vs CDAD on Eyecandies RGB+3D, 10-0 with 0 stepCDAD · Eyecandies RGB+3D, 10-0 with 0 stepI-AUROC: 79.2 -> 80.6Improved

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