A Unified Model for Multi-class Anomaly Detection
By Zhiyuan You, Lei Cui, Yujun Shen, Kai Yang, Xin Lu, Yu Zheng, Xinyi Le. Neural Information Processing Systems, 2022
501 citations recorded by the source corpus.
Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified framework. Under such a challenging setting, popular reconstruction networks may fall into an"identical shortcut", where both normal and anomalous samples can be well recovered, and hence fail to spot outliers. To tackle this obstacle, we make three improvements. First, we revisit the formulations of fully-connected layer, convolutional layer, as well as attention layer, and confirm the important role of query embedding (i.e., within attention layer) in preventing the network from learning the shortcut. We therefore come up with a layer-wise query decoder to help model the multi-class distribution. Second, we employ a neighbor masked attention module to further avoid the information leak from the input feature to the reconstructed output feature. Third, we propose a feature jittering strategy that urges the model to recover the correct message even with noisy inputs. We evaluate our algorithm on MVTec-AD and CIFAR-10 datasets, where we surpass the state-of-the-art alternatives by a sufficiently large margin. For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88.1% to 96.5%) and anomaly localization (from 89.5% to 96.8%). Code is available at https://github.com/zhiyuanyou/UniAD.
View Paper: https://www.semanticscholar.org/paper/0e8446c00ed21c19f62d71ab208a7b3601671766
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection (2023, unknown): “…2023; Roth et al., 2022; Huang et al., 2022; Mou et al., 2022; Chen et al., 2022; Bergmann et al., 2020; Pang et al., 2021a; Reiss & Hoshen, 2023; You et al., 2022; Liznerski et al., 2020; Ding et al., 2022; Zhou et al., 2023; Cao et al., 2023) and medical image analysis (Pang et al., 2021a; Qin…”
- Deep Industrial Image Anomaly Detection: A Survey (2023, unknown): “UniAD [4] L2 EfficientNet The paper trains all categories of products in one model.”
- AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models (2023, methodology): “ting of unsupervised training with a large number of normal samples, given that our method trains a single model on samples from all classes within a dataset, we selected UniAD [32], which is trained under the same setup, as a baseline for comparison.”