Rethinking Auxiliary Modalities in Multimodal Zero-shot Anomaly Detection: From Semantic Fusion to Conditional Modulation

• URL: http://arxiv.org/abs/2608.13973v1
• Date: Fri, 14 Aug 2026 05:33:45 GMT
• Title: Rethinking Auxiliary Modalities in Multimodal Zero-shot Anomaly Detection: From Semantic Fusion to Conditional Modulation
• Abstract summary: We propose a plug-and-play auxiliary-conditioned enhancement framework for zero-shot anomaly detection.<n>Our framework preserves the original RGB image-text anomaly matching pathway and uses auxiliary observations as conditional signals for RGB feature refinement.<n>Experiments on MVTec 3D-AD and Eyecandies demonstrate that our framework consistently improves multiple popular RGB-based zero-shot anomaly detectors.
• Score: 38.070045759599225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent foundation model-based methods have endowed RGB images with strong zero-shot anomaly detection (ZSAD) through vision-language pretraining. However, RGB observations alone remain limited in perceiving anomalies dominated by geometric deformation, depth variation, or subtle surface changes. Auxiliary modalities can provide complementary structural information, but existing multimodal methods typically fuse them directly into a shared semantic space, which may disturb the text-aligned anomaly semantics established by RGB foundation models and often requires modality-specific architectures. To address this issue, we propose a plug-and-play auxiliary-conditioned enhancement framework for zero-shot anomaly detection. Instead of reconstructing a joint multimodal anomaly semantic space, our framework preserves the original RGB image-text anomaly matching pathway and uses auxiliary observations as conditional signals for RGB feature refinement, allowing auxiliary modalities to seamlessly enhance existing RGB-based zero-shot anomaly detectors. Specifically, a lightweight meta-learning module takes global RGB and auxiliary representations as input and generates sample-adaptive low-rank residual updates to determine how RGB features should be refined. We further construct uncertainty-aware spatial modulation from the initial RGB anomaly response and auxiliary reliability, which determines where local residual updates are strengthened or suppressed. This global-to-local conditional modulation enables selective multimodal enhancement while preserving the original RGB anomaly semantics. Extensive experiments on MVTec 3D-AD and Eyecandies demonstrate that our framework consistently improves multiple popular RGB-based zero-shot anomaly detectors, achieving state-of-the-art performance for multimodal zero-shot anomaly detection.

Related papers

• BC-IHV: Conditioning the Color Space for Stable Rectified-Flow Low-Light Enhancement [51.79298431282401]
  Low-light image enhancement must correct ambiguous exposure without overwriting structure already supported by the input.<n>We propose Structure-Anchored Rectified Flow (SA-RF), which maintains correspondence through separate chromaticity/intensity stems.<n>We also introduce BC-IHV, a learnable Box--Cox polar color space whose analytically invertible intensity mapping controls the inverse-gradient dynamic range through a single exponent.
  arXiv  Detail & Related papers  (2026-08-22T08:43:00Z)
• Bridging Severe Cross-Modal Misalignment: End-to-End Visible-Infrared Object Detection via Explicit Feature-Domain Affine Registration [17.74037850404483]
  We propose an end-to-end visible-infrared oriented object detector tailored for severely cross-modal geometric discrepancies.<n>The proposed JFRDet achieves 69.7% $mathrmmAP_50$ on DroneVehicle Misaligned (DVMA), which represents state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-08-11T09:02:37Z)
• Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing [55.13802890769086]
  We present Evita, the first unified backbone specifically engineered for dedicated dense RGB-Event parsing.<n>To achieve profound modal synergy, Evita embeds a suite of intrinsic co-learning modules directly into every encoder layer.<n>Evita establishes new state-of-the-art metrics while delivering a superior accuracy-latency trade-off for real-time multimodal perception.
  arXiv  Detail & Related papers  (2026-07-10T06:52:09Z)
• Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking [58.338848435042536]
  RGB-Event tracking improves localization by fusing RGB appearance textures and dense temporal motion cues from event sensors.<n>Real-world scenes suffer diverse structured signal degradations that hinder traditional multi-modal fusion.<n>We present a hierarchical perturbation and retrieval framework tailored for RGB-Event tracking with robustness against partial target missing and modal degradation.
  arXiv  Detail & Related papers  (2026-06-24T23:34:06Z)
• Frequency-Guided Fusion For RGB-Thermal Semantic Segmentation [0.6187780920448871]
  We propose a multi-modal fusion architecture built upon dual ConvNeXt V2 backbones that employs stage-wise, modality-adaptive fusion strategies.<n>Experiments on MFNet and PST900 demonstrate that our lightest variant achieves 61.73% and 86.24% mIoU, respectively, with only 35.43M parameters.
  arXiv  Detail & Related papers  (2026-05-25T18:57:22Z)
• HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation [50.46910397782266]
  Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real HSIs suffer from degradations like noise, blur, and resolution loss.<n>We present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances hyperspectral image restoration by augmenting limited training images with synthetic data that closely matches the target distribution using no extra data.
  arXiv  Detail & Related papers  (2026-05-13T14:14:13Z)
• SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters [1.2622634782102324]
  Vision Foundation Models (VFMs) pretrained on large-scale RGB data have demonstrated remarkable representation quality.<n>Their applicability to multispectral imaging spanning Near-Infrared (NIR), Short-Wave Infrared (SWIR), and Long-Wave Infrared (LWIR) remains largely unexplored.<n>We present SpectraDINO, a multispectral VFM that bridges this spectral gap by extending DINOv2 ViT backbones to beyond-visible modalities.
  arXiv  Detail & Related papers  (2026-05-04T06:09:13Z)
• Spatial Orthogonal Refinement for Robust RGB-Event Visual Object Tracking [8.019596736149834]
  We propose SOR-Track, a framework for robust RGB-Event tracking based on Spatial Orthogonal Refinement (SOR)<n>Experiments on the large-scale FE108 benchmark demonstrate that SOR-Track consistently outperforms existing fusion-based trackers.<n>Despite its simplicity, the proposed method offers a principled and physics-grounded approach to multi-modal feature alignment and texture rectification.
  arXiv  Detail & Related papers  (2026-03-29T23:54:31Z)
• Unified Unsupervised Anomaly Detection via Matching Cost Filtering [113.43366521994396]
  Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data.<n>We present Unified Cost Filtering (UCF), a generic post-hoc refinement framework for refining anomaly cost volume of any UAD model.
  arXiv  Detail & Related papers  (2025-10-03T03:28:18Z)
• Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation [19.41334573257174]
  Traditional methods mostly use RGB images which are heavily affected by lighting conditions, eg, darkness. Recent studies show thermal images are robust to the night scenario as a compensating modality for segmentation. This work proposes a Residual Spatial Fusion Network (RSFNet) for RGB-T semantic segmentation.
  arXiv  Detail & Related papers  (2023-06-17T14:28:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.