.png){kind=icon}
返回
MTDiff: Visual anomaly detection with multi-scale diffusion models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112364.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Advancements in computer vision have fueled rapid developments in unsupervised anomaly detection, but current methods often encounter limitations when addressing anomalies with varying scales, and the intricate pipelines that require significant tuning efforts further hinder the usability. In this work, we propose MTDiff, a novel anomaly detection method comprising diffusion models built on different scales. In essence, the constructed scale-specific branches and their incorporation can enhance the pattern coverage, thus improving performance. MTDiff involves two parts: reconstruction that repairs the anomalous region to pseudo-normal, and detection that carefully compares and localizes the anomalies. Instead of the typical forward process of diffusion, we construct a partial Markov chain to improve the reconstruction quality. During the discrimination, we construct a simple but effective detector that operates on feature-level to better utilize the rich contextual information. MTDiff comes with a concise training pipeline, with optimized diffusion iterations ensuring the efficiency. Sufficient experiments reveal that it outperforms the state-of-the-art approaches, showing superior stability and robustness in both image- and pixel-level anomaly detection. The related code is available at https://github.com/vergilben/MTDiff.
Keyword:
Anomaly detection
Image processing
Diffusion probabilistic model
Pattern recognition
Visual application
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
BockNet: Blind-Block Reconstruction Network With a Guard Window for Hyperspectral Anomaly Detection
.png){kind=icon}
PREAI
分享收藏
分享收藏Performance enhancement of MgZnO ultraviolet photodetectors using ultrathin Al2O3 inserted layer
PREAI
分享收藏分享收藏Sensorless Control of Z Source Inverter fed BLDC Motor Drive by FOC - DTC Hybrid Control Strategy Using Fuzzy Logic Controller采用模糊逻辑控制器的foc-dtc混合控制策略的Z源逆变器馈电BLDC电机驱动的无传感器控制
PREAI
分享收藏First-Principles Computation of the Vibrational Entropy of Ordered and DisorderedNi3Al有序和无序振动熵的第一性原理计算 Ni3Al
PREAI
分享收藏
查看更多内容