mlsanityData to 7 Oct 2026

TC-MAF: Train-Calibrated Bounded Multi-Evidence Fusion for Multimodal Industrial Anomaly Detection

arXiv 2607.11170 ↗First posted 13 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Multimodal anomaly detection benefits from complementary RGB and 3D evidence, yet auxiliary RGB reconstruction is not equally reliable across product categories and class-wise test-time policy selection is usually unavailable. We propose TC-MAF, a base-anchored multi-evidence fusion design that combines a multimodal detector, complementary Dinomaly evidence, and a small cross-modal consistency cue under one fixed pixel-level fusion formula. A lightweight training-dispersion confidence (TDC) term scales auxiliary participation using only normal training statistics. On MVTec-3D, TC-MAF reaches 0.979 image-level AUROC and 0.990 pixel-level AUPRO, achieving the best mean results on both detection and localization among the compared multimodal methods. Systematic ablations show that the fusion structure itself is the dominant factor, while TDC provides a smaller but reproducible calibration gain over no calibration or arbitrary calibration. Additional experiments show that the same design remains effective under a pooled-statistics variant, auxiliary-branch and backbone substitutions, few-shot settings, a missing-3D setting, and cross-dataset evaluation on Eyecandies. Code is available at https://anonymous.4open.science/r/TC_MAF-C3BB.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 27 references that are in the map. First posted on arXiv 13 Jul 2026.

Builds on

16 of 27 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2016Wide Residual Networkscited by 3,057
  4. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  5. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  6. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  7. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 138
  8. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  9. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 74
  10. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  11. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  12. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 41
4 more
  1. 2023Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulationcited by 33
  2. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 24
  3. 2024Incomplete Multimodal Industrial Anomaly Detection via Cross-Modal Distillationcited by 6
  4. 2026Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspectivecited by 4

Built on by

Not cited yet.