type
status
date
slug
summary
tags
category
icon
password
Last edited time
Aug 7, 2024 12:25 AM
😀
2024年异常检测顶会汇总
 

📝 主旨内容

异常检测论文汇总
腾讯文档-智能表格
异常检测论文汇总
https://docs.qq.com/smartsheet/DRlZzVldnbVZkdmRC?tab=BB08J2&viewId=v60ij7
异常检测论文汇总
notion image

数据源

2024年异常检测顶会汇总
Name
Conference
Tags
affiliation
author
Datasets
Desc
PDF
Github
A Comprehensive Augmentation Framework for Anomaly Detection
AAAI2024
异常合成
重构
图像异常检测
东南大学
MVTec-AD
全面的异常合成框架 新的异常合成方法NDAA 重构和分割训练分离策略
AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
AAAI2024
少样本
扩散模型
异常生成
多模态
上海交通大学，腾讯优图实验室，宁德时代
MVTec-AD
将异常位置(掩码的编码)与异常外观(文本嵌入)分开考虑并作为条件输入到扩散模型 注意力集中在不明显区域，与掩码对齐 能够生成逼真且多样的异常 异常检查：检查，定位，分类
https://github.com/sjtuplayer/anomalydiffusion
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
AAAI2024
大语言模型
图像异常检测
多模态
少样本
中国科学院
https://github.com/CASIA-IVA-Lab/AnomalyGPT
DiAD: A Diffusion-Based Framework for Multi-Class Anomaly Detection
AAAI2024
图像异常检测
多类一模型
扩散模型
浙江大学，腾讯优图实验室
MVTec-AD
VisA
https://lewandofskee.github.io/projects/diad
Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection
AAAI2024
少样本
逻辑异常
内存库
图像异常检测
韩国大邱庆北科学技术院，斯坦福
https://github.com/oopil/PSAD_logical_anomaly_detection
Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection
AAAI2024
上海大学，复旦大学
Rethinking Reverse Distillation for Multi-Modal Anomaly Detection
AAAI2024
3D点云
多模态
上海交通大学，腾讯优图实验室
Unsupervised Continual Anomaly Detection with Contrastively-Learned Prompt
AAAI2024
扩散模型
图像异常检测
逻辑异常
对比学习
连续学习
多类一模型
南方科技大学，腾讯优图实验室，上海交通大学
MVTec-AD
MVTec LOCO
https://github.com/shirowalker/UCAD
TransFusion A Transparency-Based Diffusion Model for Anomaly Detection
ECCV2024
扩散模型
Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection
ECCV2024
3D点云
多模态
内存库
上海交通大学，腾讯优图实验室，浙江大学
MVTec-3D AD
https://arxiv.org/abs/2401.03145
R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection
ECCV2024
重构
3D点云
扩散模型
浙江大学，南洋理工大学
Real3D-AD
Anomaly-ShapeNet
https://arxiv.org/abs/2407.10862
Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection
ECCV2024
Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection
ECCV2024
GLAD Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection
ECCV2024
GeneralAD Anomaly Detection Across Domains by Attending to Distorted Features
ECCV2024
A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
ECCV2024
An Incremental Unified Framework for Small Defect Inspection
ECCV2024
Patch-Wise Augmentation for Anomaly Detection and Localization
ICASSP2024
Neural Network Training Strategy To Enhance Anomaly Detection Performance: A Perspective On Reconstruction Loss Amplification
ICASSP2024
重构
Mixed-Attention Auto Encoder for Multi-Class Industrial Anomaly Detection
ICASSP2024
Implicit Foreground-Guided Network for Anomaly Detection and Localization
ICASSP2024
CAGEN: Controllable Anomaly Generator using Diffusion Model
ICASSP2024
扩散模型
Feature-Constrained and Attention-Conditioned Distillation Learning for Visual Anomaly Detection
ICASSP2024
A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation
ICASSP2024
重构
Long-Tailed Anomaly Detection with Learnable Class Names
CVPR2024
Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping
CVPR2024
少样本
多模态
3D点云
博洛尼亚大学(意大利)
https://arxiv.org/abs/2312.04521
https://github.com/CVLAB-Unibo/crossmodal-feature-mapping
PromptAD Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
CVPR2024
Real-IAD A Real-World Multi-view Dataset for Benchmarking Versatile Industrial Anomaly Detection
CVPR2024
RealNet A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
CVPR2024
Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
CVPR2024
CLIP
多模态
少样本
零样本
正常生成
首尔中央大学，韩国LG CNS公司生成式人工智能团队
https://github.com/MingyuLee82/TGI_AD_v1
Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts
CVPR2024
Towards Scalable 3D Anomaly Detection and Localization A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network
CVPR2024
3D点云
数据集
上海理工大学，密歇根大学安娜堡分校
https://arxiv.org/abs/2311.14897
https://github.com/Chopper-233/Anomaly-ShapeNet
 

🤗 总结归纳

 

📎 参考文章

 
相关文章
科研全流程加速——让AI为你插上翅膀
PatchCore内存库中核心集的选择
Transformer中的位置编码
AnomalyDiffusion(AAAI2024)
Control Net：控制增强的微调方法
通用异常检测新曙光：GPT-4V的全方位异常检测表现
Transformer中的位置编码南京景点及美食推荐(三日游)
Loading...