Copertina

Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhan, Jiawei, Lai, Jinxiang, Gao, Bin-Bin, Liu, Jun, Chen, Xiaochen, Wang, Chengjie
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MatchDet: A Collaborative Framework for Image Matching and Object Detection
di: Lai, Jinxiang, et al.
Pubblicazione: (2023)

Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
di: Gao, Bin-Bin, et al.
Pubblicazione: (2025)

Clustered-patch Element Connection for Few-shot Learning
di: Lai, Jinxiang, et al.
Pubblicazione: (2023)

One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
di: Gao, Bin-Bin, et al.
Pubblicazione: (2026)

Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection
di: Fan, Yuanting, et al.
Pubblicazione: (2025)

DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning
di: Zhan, Jiawei, et al.
Pubblicazione: (2025)

Large-Scale Universal Defect Generation: Foundation Models and Datasets
di: Fan, Yuanting, et al.
Pubblicazione: (2026)

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
di: Gui, Guan, et al.
Pubblicazione: (2025)

BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation
di: Lai, Jinxiang, et al.
Pubblicazione: (2025)

Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces
di: Feng, Yaoxuan, et al.
Pubblicazione: (2026)

tSF: Transformer-based Semantic Filter for Few-Shot Learning
di: Lai, Jinxiang, et al.
Pubblicazione: (2022)

Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection
di: Wang, Chengjie, et al.
Pubblicazione: (2024)

SoftPatch: Unsupervised Anomaly Detection with Noisy Data
di: Jiang, Xi, et al.
Pubblicazione: (2024)

Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt
di: Liu, Jiaqi, et al.
Pubblicazione: (2024)

Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt
di: Gao, Bin-Bin
Pubblicazione: (2025)

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
di: Gao, Bin-Bin, et al.
Pubblicazione: (2025)

AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
di: Jiang, Xi, et al.
Pubblicazione: (2026)

SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning
di: Lai, Jinxiang, et al.
Pubblicazione: (2023)

Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
di: Jiang, Xi, et al.
Pubblicazione: (2024)

SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
di: Wang, Chengjie, et al.
Pubblicazione: (2024)

DCDB: Dynamic Conditional Dual Diffusion Bridge for Ill-posed Multi-Tasks
di: Huang, Chengjie, et al.
Pubblicazione: (2025)

Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection
di: Wang, Hongsong, et al.
Pubblicazione: (2024)

ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning
di: Tan, Xiaofeng, et al.
Pubblicazione: (2026)

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
di: Hu, Teng, et al.
Pubblicazione: (2023)

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
di: Jiang, Xi, et al.
Pubblicazione: (2024)

Memory-Augmented Dual-Decoder Networks for Multi-Class Unsupervised Anomaly Detection
di: Xing, Jingyu, et al.
Pubblicazione: (2025)

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
di: Tan, Xiaofeng, et al.
Pubblicazione: (2026)

Learning Multi-view Anomaly Detection with Efficient Adaptive Selection
di: He, Haoyang, et al.
Pubblicazione: (2024)

CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
di: Chen, Xuhai, et al.
Pubblicazione: (2023)

Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection
di: Zhang, Jiangning, et al.
Pubblicazione: (2023)

VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
di: Hicsonmez, Samet, et al.
Pubblicazione: (2025)

Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignment
di: Guo, Jia, et al.
Pubblicazione: (2024)

MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
di: Gao, Bin-Bin
Pubblicazione: (2025)

AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model
di: Yan, Zhenyu, et al.
Pubblicazione: (2024)

Anomaly Detection with Conditioned Denoising Diffusion Models
di: Mousakhan, Arian, et al.
Pubblicazione: (2023)

Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era
di: Zhu, Wenbing, et al.
Pubblicazione: (2025)

Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection
di: Cheng, Yuqi, et al.
Pubblicazione: (2025)

DMAD: Dual Memory Bank for Real-World Anomaly Detection
di: Hu, Jianlong, et al.
Pubblicazione: (2024)

A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection
di: Zhang, Jiangning, et al.
Pubblicazione: (2024)

Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection
di: He, Liren, et al.
Pubblicazione: (2024)