paper-with-me

Papers

SoftPatch: Unsupervised Anomaly Detection with Noisy Data

2024-03-21 · NeurIPS 2022 11 · Xi Jiang, Ying Chen, Qiang Nie, Yong liu, Jianlin Liu, Bin-Bin Gao, Jun Liu, Chengjie Wang, Feng Zheng

Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an inevitable problem in real-world anomaly detection but is seldom discussed. This paper considers label-level noise in image sensory anomaly detection for the first time. To solve this problem, we proposed a memory-based unsupervised AD method, SoftPatch, which efficiently denoises the data at the patch level. Noise discriminators are utilized to generate outlier scores for patch-level noise elimination before coreset construction. The scores are then stored in the memory bank to soften the anomaly detection boundary. Compared with existing methods, SoftPatch maintains a strong modeling ability of normal data and alleviates the overconfidence problem in coreset. Comprehensive experiments in various noise scenes demonstrate that SoftPatch outperforms the state-of-the-art AD methods on the MVTecAD and BTAD benchmarks and is comparable to those methods under the setting without noise.

📄 PDF Abstract BibTeX arXiv:2403.14233

Code (1)

TencentYoutuResearch/AnomalyDetection-SoftPatch 공식 구현 pytorch

Tasks

Anomaly DetectionUnsupervised Anomaly Detection

Similar Papers 제목 키워드 기반

SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation

2024-12-30 · Chengjie Wang, Xi Jiang, Bin-Bin Gao, Zhenye Gan 외

Although mainstream unsupervised anomaly detection (AD) (including image-level classification and pixel-level segmentation)algorithms perform well in academic datasets, their performance is limited in practical applicati…

Anomaly ClassificationAnomaly DetectionClassificationUnsupervised Anomaly Detection

Unsupervised Anomaly Detection Ensembles using Item Response Theory

2021-06-11 · Sevvandi Kandanaarachchi

Constructing an ensemble from a heterogeneous set of unsupervised anomaly detection methods is challenging because the class labels or the ground truth is unknown. Thus, traditional ensemble techniques that use the respo…

Anomaly DetectionUnsupervised Anomaly Detection

A Synergy Scoring Filter for Unsupervised Anomaly Detection with Noisy Data

2025-02-19 · Chengming Liu, Fengjie Wang, Lei Shi, Zhe Zhao

Noise-inclusive fully unsupervised anomaly detection (FUAD) holds significant practical relevance. Although various methods exist to address this problem, they are limited in both performance and scalability. Our work se…

Anomaly DetectionUnsupervised Anomaly Detection

M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising

2024-06-04 · Chengjie Wang, Haokun Zhu, Jinlong Peng, Yue Wang 외

Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images. Yet, both RGB and 3D data are crucial for anomaly detection, and the datasets are seldom completely c…

Anomaly DetectionDenoising

TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

2025-04-03 · CVPR 2025 1 · Yoon Gyo Jung, Jaewoo Park, Jaeho Yoon, Kuan-Chuan Peng 외

We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We obse…

Anomaly DetectionUnsupervised Anomaly Detection