MATCH is the first flow matching method for multi-view anomaly detection, reporting SOTA results on Real-IAD and the first comprehensive evaluation on MANTA-Tiny while enabling real-time use by omitting the divergence term.
hub
Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
FIDeL detects failures in imitation learning by building compact nominal representations via optimal transport, applying conformal prediction thresholds, and using VLMs for semantic filtering, outperforming baselines by 5.3% AUROC and 17.38% accuracy on the new BotFails dataset.
Introduces scenarios and metrics for ambiguous normal samples in anomaly detection plus RePaste method achieving SOTA on the new metric on MVTec AD while retaining high AUROC and PRO.
A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.
Coupling-subnet LoRA isolation plus TSA/ACL/TAL yields SOTA continual anomaly detection (98.4% MVTec, 93% VisA I-AUC) with parameter-level zero forgetting under correct routing.
LogiCo is a unified framework using component-level feature reconstruction to detect both logical and structural anomalies, achieving SOTA results on four benchmarks with code publicly available.
Hypergraph model on DINOv2 tokens raises logical anomaly AUROC to 0.9279 on MVTec LOCO breakfast-box data by scoring an information quotient across local, relational, and hyperedge evidence.
SPUNA leverages spectral neighborhood annotation on visual feature manifolds to enable robust PU learning for covariate shift detection, matching fully supervised performance.
A new framework learns low-dimensional subspaces from nominal samples and reconstructs target deep embeddings via self-expressive linear combinations to localize anomalies, claiming SOTA on three benchmarks.
LiZAD reduces memory by 61.5%, parameters by 74.6%, and latency by 3.02x versus six prior ZSAD models while incurring only a 6.4% average P-AUROC drop on VisA, BTAD, MPDD, and MVTec-AD, with successful Jetson deployment.
IndusAgent achieves state-of-the-art zero-shot performance on industrial anomaly benchmarks by using a custom Indus-CoT dataset, dynamic tool orchestration, and gated RL to optimize anomaly classification, localization, and reasoning.
ZSG-IAD is a zero-shot multimodal system that uses language-guided two-hop grounding and rule-based reinforcement learning to produce anomaly masks and explainable reports from industrial sensor data.
MambaADv2 evolves Mamba state space models with hybrid blocks, frequency convolutions, and adaptive scanning for improved unsupervised anomaly detection.
Unsupervised anomaly detection with pre-trained Anomalib models achieves F1 macro score over 0.95 on Raspberry Pi using 10 images and 90 seconds training time.
Fine-tuned YOLOv8 with TensorRT/OpenVINO optimizations reaches over 120 FPS and 98.5% mAP on NEU, MVTec AD, and custom automotive defect datasets for edge deployment.
citing papers explorer
-
MATCH: Flow Matching for Multi-View Anomaly Detection
MATCH is the first flow matching method for multi-view anomaly detection, reporting SOTA results on Real-IAD and the first comprehensive evaluation on MANTA-Tiny while enabling real-time use by omitting the divergence term.
-
Failure Identification in Imitation Learning Via Statistical and Semantic Filtering
FIDeL detects failures in imitation learning by building compact nominal representations via optimal transport, applying conformal prediction thresholds, and using VLMs for semantic filtering, outperforming baselines by 5.3% AUROC and 17.38% accuracy on the new BotFails dataset.
-
Novel Anomaly Detection Scenarios and Evaluation Metrics to Address the Ambiguity in the Definition of Normal Samples
Introduces scenarios and metrics for ambiguous normal samples in anomaly detection plus RePaste method achieving SOTA on the new metric on MVTec AD while retaining high AUROC and PRO.
-
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.
-
DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
Coupling-subnet LoRA isolation plus TSA/ACL/TAL yields SOTA continual anomaly detection (98.4% MVTec, 93% VisA I-AUC) with parameter-level zero forgetting under correct routing.
-
LogiCo: A Unified Framework for Logical and Structural Anomaly Detection
LogiCo is a unified framework using component-level feature reconstruction to detect both logical and structural anomalies, achieving SOTA results on four benchmarks with code publicly available.
-
Hypergraph Normal World Models for Logical Visual Anomaly Detection
Hypergraph model on DINOv2 tokens raises logical anomaly AUROC to 0.9279 on MVTec LOCO breakfast-box data by scoring an information quotient across local, relational, and hyperedge evidence.
-
From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
SPUNA leverages spectral neighborhood annotation on visual feature manifolds to enable robust PU learning for covariate shift detection, matching fully supervised performance.
-
Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization
A new framework learns low-dimensional subspaces from nominal samples and reconstructs target deep embeddings via self-expressive linear combinations to localize anomalies, claiming SOTA on three benchmarks.
-
LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing
LiZAD reduces memory by 61.5%, parameters by 74.6%, and latency by 3.02x versus six prior ZSAD models while incurring only a 6.4% average P-AUROC drop on VisA, BTAD, MPDD, and MVTec-AD, with successful Jetson deployment.
-
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
IndusAgent achieves state-of-the-art zero-shot performance on industrial anomaly benchmarks by using a custom Indus-CoT dataset, dynamic tool orchestration, and gated RL to optimize anomaly classification, localization, and reasoning.
-
ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection
ZSG-IAD is a zero-shot multimodal system that uses language-guided two-hop grounding and rule-based reinforcement learning to produce anomaly masks and explainable reports from industrial sensor data.
-
MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection
MambaADv2 evolves Mamba state space models with hybrid blocks, frequency convolutions, and adaptive scanning for improved unsupervised anomaly detection.
-
Leveraging Unsupervised Learning for Cost-Effective Visual Anomaly Detection
Unsupervised anomaly detection with pre-trained Anomalib models achieves F1 macro score over 0.95 on Raspberry Pi using 10 images and 90 seconds training time.
-
Real-Time Industrial Defect Detection on Edge Hardware Using Fine-Tuned YOLOv8: A Systematic Benchmark on the NEU Surface Defect Database and MVTec AD with Automotive & Battery Manufacturing Extensions
Fine-tuned YOLOv8 with TensorRT/OpenVINO optimizations reaches over 120 FPS and 98.5% mAP on NEU, MVTec AD, and custom automotive defect datasets for edge deployment.
- $\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors