CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection

• URL: http://arxiv.org/abs/2606.20300v3
• Date: Wed, 24 Jun 2026 05:50:53 GMT
• Title: CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection
• Abstract summary: Few-shot anomaly detection remains challenging due to limited training data.<n>We present CMDS-AD, a Cross-Modal Dual-Stream Anomaly Detection framework.<n> CMDS-AD achieves absolute performance gains of 5.7% (I-AUROC) and 2.0% (AUPRO) on MVTec 3D-AD, alongside 7.7% and 5.6% improvements on EyeCandies.
• Score: 22.190054508477704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-shot anomaly detection remains challenging due to limited training data. Multi-modal anomaly detection (MAD) offers a viable solution, leveraging 3D geometric cues to enrich 2D RGB representations and compensate for this scarcity. However, existing MAD methods apply spatially uniform feature processing, conflating stable macroscopic structures with high-frequency localized defect signals, exacerbating cross-modal misalignment and inflating false-positive rates. To overcome this, we present CMDS-AD, a Cross-Modal Dual-Stream Anomaly Detection framework. A LoRA-guided diffusion model generates diverse RGB samples to mitigate extreme data scarcity. For 3D normal augmentation, we employ a pre-trained diffusion model as a normal estimator. Crucially, this estimator inherently acts as a non-linear low-pass filter, directly extracting low-frequency normal representations from RGB inputs. This establishes an auxiliary estimated stream of purely low-frequency information, anchoring robust structural templates and assisting the uncompressed real stream, containing coupled high- and low-frequency components, to precisely isolate micro-defects. A Coordinate-Aware Hierarchical Feature Mapper adaptively aligns cross-modal semantics, while a multiplicative scoring mechanism filters modality-specific noise. Under the extreme 1-shot setting, CMDS-AD achieves absolute performance gains of 5.7% (I-AUROC) and 2.0% (AUPRO) on MVTec 3D-AD, alongside 7.7% and 5.6% improvements on EyeCandies, establishing a new state-of-the-art. Code is available at https://github.com/Junhaocai27/CMDS-AD

Related papers

• Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs [59.973833105841685]
  A key challenge for improving adversarial transferability is to effectively capture the intrinsic visual focus shared across different models.<n>We propose FRA-Attack, which addresses both challenges from a unified frequency-domain regularization perspective.<n>For feature alignment, a high-pass DCT objective on patch features suppresses redundant global structures and concentrates the loss on the high-frequency band that carries the MLLMs' intrinsic visual focus.<n>For gradient optimization, we introduce Frequency-domain Gradient Regularization (FGR), a textitmodel-agnostic low-pass regularizer that modulates the surrogate gradient using
  arXiv  Detail & Related papers  (2026-05-20T08:15:56Z)
• Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models [0.3078691410268859]
  Diffusion models are rapidly redefining 3D anomaly detection in point cloud data.<n>We introduce a novel hybrid loss formulation that explicitly enforces reconstruction toward clean data.<n>This design substantially reduces inference cost, achieving up to 80x faster runtime than the current state-of-the-art method.
  arXiv  Detail & Related papers  (2026-05-06T18:52:53Z)
• DFIR-DETR: Frequency Domain Enhancement and Dynamic Feature Aggregation for Cross-Scene Small Object Detection [16.16000521213211]
  Small object detection in UAV remote sensing images is difficult.<n>Current transformer-based detectors struggle with three critical issues.<n>We introduce DFIR-DETR to tackle these problems through dynamic feature aggregation combined with frequency-domain processing.
  arXiv  Detail & Related papers  (2025-12-08T01:25:10Z)
• Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models [1.1487074612765584]
  We introduce Reconstruction-free Anomaly Detection with Attention-based diffusion models in Real-time (RADAR)<n>RADAR overcomes the limitations of reconstruction-based anomaly detection.<n>We evaluate RADAR on real-world 3D-printed material and the MVTec-AD dataset.
  arXiv  Detail & Related papers  (2025-08-06T18:56:08Z)
• UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation [17.289252835606533]
  Uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed.<n> UDHF2-Net is a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP)<n>Mask-and-geo-knowledge-based uncertainty diffusion module (MUDM) is a self-supervised learning strategy.<n>A frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection.
  arXiv  Detail & Related papers  (2024-06-23T15:03:35Z)
• DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection [52.74152717667157]
  We propose a lightweight module called Dual Attention Module (DAM) for capturing cross-dimension interaction relationships in-temporal skeletal data. It employs the frame attention mechanism to identify the most significant frames and the skeleton attention mechanism to capture broader relationships across fixed partitions with minimal parameters and flops.
  arXiv  Detail & Related papers  (2024-06-05T06:18:03Z)
• M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising [63.39134873744748]
  Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images. This paper proposes a novel noise-resistant M3DM-NR framework to leverage strong multi-modal discriminative capabilities of CLIP. Extensive experiments show that M3DM-NR outperforms state-of-the-art methods in 3D-RGB multi-modal noisy anomaly detection.
  arXiv  Detail & Related papers  (2024-06-04T12:33:02Z)
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
  We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
  arXiv  Detail & Related papers  (2024-01-06T07:30:41Z)
• Adaptive Multi-step Refinement Network for Robust Point Cloud Registration [82.64560249066734]
  Point Cloud Registration estimates the relative rigid transformation between two point clouds of the same scene.<n>We propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step.<n>Our method achieves state-of-the-art performance on both the 3DMatch/3DLoMatch and KITTI benchmarks.
  arXiv  Detail & Related papers  (2023-12-05T18:59:41Z)
• Multimodal Industrial Anomaly Detection via Hybrid Fusion [59.16333340582885]
  We propose a novel multimodal anomaly detection method with hybrid fusion scheme. Our model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTecD-3 AD dataset.
  arXiv  Detail & Related papers  (2023-03-01T15:48:27Z)
• Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown-View Tomography [58.60249163402822]
  Unknown-view tomography (UVT) reconstructs a 3D density map from its 2D projections at unknown, random orientations. The proposed OMR is more robust and performs significantly better than the previous state-of-the-art OMR approach.
  arXiv  Detail & Related papers  (2022-07-06T21:40:59Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)

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.