PADiff: Reconstruction From Patch to Pixel With Normality-Guided Diffusion Model for Unsupervised Anomaly Localization

正态性 异常(物理) 像素 异常检测 人工智能 扩散 计算机科学 模式识别(心理学) 计算机视觉 数学 物理 统计 热力学 凝聚态物理
作者
Zuo Zuo,Jiahao Dong,Yao Wu,Yanyun Qu,Zongze Wu
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:36 (10): 18558-18571 被引量:2
标识
DOI:10.1109/tnnls.2025.3572438
摘要

Anomaly localization (AL) is an indispensable and challenging task in manufacturing. Recently, diffusion models have been widely used to localize anomalies through discrepancies between original and reconstructed representations, which is based on the hypothesis that diffusion models regard anomalies as noise and reconstruct them to normal representations. However, anomalies usually deviate from prior standard Gaussian distribution and diffusion models cannot reconstruct anomaly parts as normal patterns well due to powerful generalization. These issues hinder the application of diffusion models in AL and lead to suboptimal performance. As a remedy, we present a novel framework for AL based on the diffusion model, dubbed PADiff. To enable the diffusion model to reconstruct abnormal regions to normal regions in an anomaly image, we propose to guide the diffusion model in the reconstruction process using its normal counterpart. High-quality guided normal counterpart plays a key role in our method. Therefore, we propose a patch-substitution strategy to obtain a high-quality-guided normal counterpart. Specifically, we first construct a normal patch memory bank using normal training samples. With a normal memory bank, we find potential anomaly patches in testing images and substitute them with most similar normal patches in the memory bank. After substitution, pseudo-normal images are generated to guide the diffusion model. To make our method more data-efficient, we divide an image into patches and propose patch-wise training and reconstruction. As one of our innovations, we propose to encode each patch into positional embedding and add it on time embedding, which introduces patch-level representation and position information in the diffusion model. Extensive experiments are conducted on three commonly used anomaly detection datasets (MVTec-AD, VisA, and BTAD) to showcase the state-of-the-art (SOTA) performance of the proposed PADiff. The source code is publicly available at https://github.com/Jay-zzcoder/padiff.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
科研通AI6.3的应助被Zoey采纳,获得30
刚刚
没得发布了新的文献求助10
2秒前
2秒前
牧青发布了新的文献求助20
2秒前
寒冷灰狼完成签到,获得积分10
3秒前
FashionBoy的应助被yugui采纳,获得10
3秒前
huangping完成签到,获得积分10
3秒前
情怀的应助被鱼鱼鱼采纳,获得10
3秒前
欣喜忆曼完成签到,获得积分10
3秒前
Mortal发布了新的文献求助10
3秒前
丁真珍珠发布了新的文献求助10
4秒前
土多多的应助被雨竹采纳,获得10
5秒前
文艺雁梅完成签到,获得积分10
5秒前
鱿鱼坤完成签到,获得积分20
5秒前
6秒前
6秒前
白白关注了科研通微信公众号
6秒前
7秒前
7秒前
有魅力猕猴桃完成签到,获得积分20
7秒前
liko发布了新的文献求助10
7秒前
忧心的妙之完成签到,获得积分10
8秒前
海洲完成签到 ,获得积分10
9秒前
9秒前
10秒前
酷酷的悒发布了新的文献求助10
12秒前
Ava的应助被孤独星月采纳,获得10
15秒前
言宴完成签到 ,获得积分10
15秒前
丘比特的应助被han采纳,获得10
15秒前
17秒前
17秒前
17秒前
东方元语发布了新的文献求助20
18秒前
所所的应助被科研通管家采纳,获得10
19秒前
顾矜的应助被18756828852采纳,获得10
19秒前
观山青发布了新的文献求助10
19秒前
酷波er的应助被科研通管家采纳,获得10
19秒前
xiaochaoge完成签到,获得积分10
19秒前
今后的应助被科研通管家采纳,获得10
19秒前
SciGPT的应助被科研通管家采纳,获得10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Agyptische Geschichte der 21.30. Dynastie 510
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8192723
求助须知:如何正确求助?哪些是违规求助? 9579144
关于积分的说明 21863903
捐赠科研通 7792268
什么是DOI,文献DOI怎么找? 3437013
关于科研通互助平台的介绍 2560633
邀请新用户注册赠送积分活动 2483864