Imagen de Portada

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gu, Zhaopeng, Zhu, Bingke, Zhu, Guibo, Chen, Yingying, Tang, Ming, Wang, Jinqiao
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
por: Gu, Zhaopeng, et al.
Publicado: (2025)

FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
por: Gu, Zhaopeng, et al.
Publicado: (2025)

FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization
por: Gu, Zhaopeng, et al.
Publicado: (2024)

MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection
por: Qian, Long, et al.
Publicado: (2025)

Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection
por: Qian, Long, et al.
Publicado: (2025)

LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing
por: Wang, Langyu, et al.
Publicado: (2024)

MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing
por: Wang, Langyu, et al.
Publicado: (2025)

Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
por: Zhang, Enming, et al.
Publicado: (2024)

MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation
por: Zhu, Yuanbing, et al.
Publicado: (2024)

Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning
por: Wang, Linge, et al.
Publicado: (2026)

EventVAD: Training-Free Event-Aware Video Anomaly Detection
por: Shao, Yihua, et al.
Publicado: (2025)

Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework
por: Kamide, Koichiro, et al.
Publicado: (2025)

Monocular Lane Detection Based on Deep Learning: A Survey
por: He, Xin, et al.
Publicado: (2024)

AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
por: Zhang, Yi, et al.
Publicado: (2026)

ComplexVAD: Detecting Interaction Anomalies in Video
por: Mumcu, Furkan, et al.
Publicado: (2025)

Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts
por: Zhu, Jiawen, et al.
Publicado: (2024)

A Benchmark for Crime Surveillance Video Analysis with Large Models
por: Chen, Haoran, et al.
Publicado: (2025)

Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection
por: Chen, Xinyi, et al.
Publicado: (2024)

Few-shot Online Anomaly Detection and Segmentation
por: Wei, Shenxing, et al.
Publicado: (2024)

VAD4Space: Visual Anomaly Detection for Planetary Surface Imagery
por: Genilotti, Fabrizio, et al.
Publicado: (2026)

Auto DragGAN: Editing the Generative Image Manifold in an Autoregressive Manner
por: Cai, Pengxiang, et al.
Publicado: (2024)

BFRFormer: Transformer-based generator for Real-World Blind Face Restoration
por: Ge, Guojing, et al.
Publicado: (2024)

Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
por: Bahram, Yara, et al.
Publicado: (2025)

Dual-path Frequency Discriminators for Few-shot Anomaly Detection
por: Bai, Yuhu, et al.
Publicado: (2024)

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
por: Huang, Chao, et al.
Publicado: (2026)

ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications
por: Zhu, Tao, et al.
Publicado: (2025)

DUAL-VAD: Dual Benchmarks and Anomaly-Focused Sampling for Video Anomaly Detection
por: Jung, Seoik, et al.
Publicado: (2025)

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
por: Ma, Kexin, et al.
Publicado: (2026)

MAUP: Training-free Multi-center Adaptive Uncertainty-aware Prompting for Cross-domain Few-shot Medical Image Segmentation
por: Zhu, Yazhou, et al.
Publicado: (2025)

Search is All You Need for Few-shot Anomaly Detection
por: Wang, Qishan, et al.
Publicado: (2025)

MadCLIP: Few-shot Medical Anomaly Detection with CLIP
por: Shiri, Mahshid, et al.
Publicado: (2025)

FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
por: Li, Yuanwei, et al.
Publicado: (2024)

UniADC: A Unified Framework for Anomaly Detection and Classification
por: Zhang, Ximiao, et al.
Publicado: (2025)

Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection
por: Zhu, Jiaqi, et al.
Publicado: (2024)

FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
por: Liu, Tongkun, et al.
Publicado: (2023)

AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2
por: Damm, Simon, et al.
Publicado: (2024)

UniFS: Universal Few-shot Instance Perception with Point Representations
por: Jin, Sheng, et al.
Publicado: (2024)

UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
por: Bai, Chengyu, et al.
Publicado: (2025)

CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
por: Lim, Hyeongmuk, et al.
Publicado: (2026)

HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detection
por: Hemmatyar, Mohammad Mahdi, et al.
Publicado: (2025)