Papers › Attention Guided Anomaly Localization in Images

Attention Guided Anomaly Localization in Images

19 Nov 2019ECCV 2020 8arXiv:1911.08616archive 2025-07-28

Shashanka Venkataramanan, Kuan-Chuan Peng, Rajat Vikram Singh, Abhijit Mahalanobis

Anomaly localization is an important problem in computer vision which involves localizing anomalous regions within images with applications in industrial inspection, surveillance, and medical imaging. This task is challenging due to the small sample size and pixel coverage of the anomaly in real-world scenarios. Most prior works need to use anomalous training images to compute a class-specific threshold to localize anomalies. Without the need of anomalous training images, we propose Convolutional Adversarial Variational autoencoder with Guided Attention (CAVGA), which localizes the anomaly with a convolutional latent variable to preserve the spatial information. In the unsupervised setting, we propose an attention expansion loss where we encourage CAVGA to focus on all normal regions in the image. Furthermore, in the weakly-supervised setting we propose a complementary guided attention loss, where we encourage the attention map to focus on all normal regions while minimizing the attention map corresponding to anomalous regions in the image. CAVGA outperforms the state-of-the-art (SOTA) anomaly localization methods on MVTec Anomaly Detection (MVTAD), modified ShanghaiTech Campus (mSTC) and Large-scale Attention based Glaucoma (LAG) datasets in the unsupervised setting and when using only 2% anomalous images in the weakly-supervised setting. CAVGA also outperforms SOTA anomaly detection methods on the MNIST, CIFAR-10, Fashion-MNIST, MVTAD, mSTC and LAG datasets.

PaperPDFConference PDF

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 Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection MVTec AD CAVGA-R (weakly-supervised) Segmentation AUROC 93 #140 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CAVGA-D (weakly-supervised) Segmentation AUROC 92 #141 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CAVGA-R (unsupervised) Segmentation AUROC 89 #143 of 148 Archive leaderboard report
Anomaly Detection MVTec AD CAVGA-D (unsupervised) Segmentation AUROC 85 #145 of 148 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.

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