Papers › Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers

Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers

6 Jun 2023arXiv:2306.03492archive 2025-07-28

Hanxi Li, Jingqi Wu, Deyin Liu, Lin Wu, Hao Chen, Mingwen Wang, Chunhua Shen

Recent advancements in industrial anomaly detection (AD) have demonstrated that incorporating a small number of anomalous samples during training can significantly enhance accuracy. However, this improvement often comes at the cost of extensive annotation efforts, which are impractical for many real-world applications. In this paper, we introduce a novel framework, Weak}ly-supervised RESidual Transformer (WeakREST), designed to achieve high anomaly detection accuracy while minimizing the reliance on manual annotations. First, we reformulate the pixel-wise anomaly localization task into a block-wise classification problem. Second, we introduce a residual-based feature representation called Positional Fast Anomaly Residuals (PosFAR) which captures anomalous patterns more effectively. To leverage this feature, we adapt the Swin Transformer for enhanced anomaly detection and localization. Additionally, we propose a weak annotation approach, utilizing bounding boxes and image tags to define anomalous regions. This approach establishes a semi-supervised learning context that reduces the dependency on precise pixel-level labels. To further improve the learning process, we develop a novel ResMixMatch algorithm, capable of handling the interplay between weak labels and residual-based representations. On the benchmark dataset MVTec-AD, our method achieves an Average Precision (AP) of 83.0%, surpassing the previous best result of 82.7% in the unsupervised setting. In the supervised AD setting, WeakREST attains an AP of 87.6%, outperforming the previous best of 86.0%. Notably, even when using weaker annotations such as bounding boxes, WeakREST exceeds the performance of leading methods relying on pixel-wise supervision, achieving an AP of 87.1% compared to the prior best of 86.0% on MVTec-AD.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionAnomaly LocalizationSupervised Anomaly DetectionUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection BTAD WeakREST-Un Detection AUROC 94.4 #10 of 15 Archive leaderboard report
Anomaly Detection BTAD WeakREST-Un Segmentation AP 63.1 #10 of 15 Archive leaderboard report
Anomaly Detection BTAD WeakREST-Un Segmentation AUPRO 84.9 #10 of 15 Archive leaderboard report
Anomaly Detection BTAD WeakREST-Un Segmentation AUROC 98.7 #10 of 15 Archive leaderboard report
Anomaly Detection MVTec AD WeakREST-Un Detection AUROC 99.6 #18 of 148 Archive leaderboard report
Anomaly Detection MVTec AD WeakREST-Un FPS 25.2 #18 of 148 Archive leaderboard report
Anomaly Detection MVTec AD WeakREST-Un Segmentation AP 83.0 #18 of 148 Archive leaderboard report
Anomaly Detection MVTec AD WeakREST-Un Segmentation AUPRO 97.6 #18 of 148 Archive leaderboard report
Anomaly Detection MVTec AD WeakREST-Un Segmentation AUROC 99.3 #18 of 148 Archive leaderboard report
Supervised Anomaly Detection BTAD WeakREST-Block Detection AUROC 96.5 #2 of 2 Archive leaderboard report
Supervised Anomaly Detection BTAD WeakREST-Block Segmentation AP 84.6 #2 of 2 Archive leaderboard report
Supervised Anomaly Detection BTAD WeakREST-Block Segmentation AUPRO 90.8 #2 of 2 Archive leaderboard report
Supervised Anomaly Detection BTAD WeakREST-Block Segmentation AUROC 99.3 #2 of 2 Archive leaderboard report
Supervised Anomaly Detection MVTec AD WeakREST-Block Detection AUROC 99.8 #1 of 8 Archive leaderboard report
Supervised Anomaly Detection MVTec AD WeakREST-Block Segmentation AP 87.6 #1 of 8 Archive leaderboard report
Supervised Anomaly Detection MVTec AD WeakREST-Block Segmentation AUPRO 98.4 #1 of 8 Archive leaderboard report
Supervised Anomaly Detection MVTec AD WeakREST-Block Segmentation AUROC 99.7 #1 of 8 Archive leaderboard report
Unsupervised Anomaly Detection KolektorSDD2 WeakREST-Un Segmentation AP 76.9 #1 of 3 Archive leaderboard report
Unsupervised Anomaly Detection KolektorSDD2 WeakREST-Un Segmentation AUPRO 98.5 #1 of 3 Archive leaderboard report
Unsupervised Anomaly Detection KolektorSDD2 WeakREST-Un Segmentation AUROC 99.7 #1 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections