</> Code with Papers by Syntology

Papers › PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation

PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation

12 Oct 2020CVPR 2021 1arXiv:2010.05903archive 2025-07-28

Tal Reiss, Niv Cohen, Liron Bergman, Yedid Hoshen

Anomaly detection methods require high-quality features. In recent years, the anomaly detection community has attempted to obtain better features using advances in deep self-supervised feature learning. Surprisingly, a very promising direction, using pretrained deep features, has been mostly overlooked. In this paper, we first empirically establish the perhaps expected, but unreported result, that combining pretrained features with simple anomaly detection and segmentation methods convincingly outperforms, much more complex, state-of-the-art methods. In order to obtain further performance gains in anomaly detection, we adapt pretrained features to the target distribution. Although transfer learning methods are well established in multi-class classification problems, the one-class classification (OCC) setting is not as well explored. It turns out that naive adaptation methods, which typically work well in supervised learning, often result in catastrophic collapse (feature deterioration) and reduce performance in OCC settings. A popular OCC method, DeepSVDD, advocates using specialized architectures, but this limits the adaptation performance gain. We propose two methods for combating collapse: i) a variant of early stopping that dynamically learns the stopping iteration ii) elastic regularization inspired by continual learning. Our method, PANDA, outperforms the state-of-the-art in the OCC, outlier exposure and anomaly segmentation settings by large margins.

PaperPDFConference PDFCode

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

Code

talreiss/PANDA officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Anomaly DetectionAnomaly SegmentationContinual LearningMulti-class ClassificationOne-Class ClassificationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Cats-and-Dogs PANDA ROC AUC 97.3 #1 of 4 Archive leaderboard report
Anomaly Detection Cats-and-Dogs PANDA-OE ROC AUC 94.5 #2 of 4 Archive leaderboard report
Anomaly Detection Cats-and-Dogs Self-Supervised One-class SVM, RBF kernel ROC AUC 51.7 #3 of 4 Archive leaderboard report
Anomaly Detection Cats-and-Dogs Self-Supervised DeepSVDD ROC AUC 50.5 #4 of 4 Archive leaderboard report
Anomaly Detection DIOR PANDA-OE ROC AUC 95.9 #1 of 4 Archive leaderboard report
Anomaly Detection DIOR PANDA ROC AUC 94.3 #2 of 4 Archive leaderboard report
Anomaly Detection DIOR Self-Supervised One-class SVM, RBF kernel ROC AUC 70.7 #3 of 4 Archive leaderboard report
Anomaly Detection DIOR Self-Supervised DeepSVDD ROC AUC 70 #4 of 4 Archive leaderboard report
Anomaly Detection Fashion-MNIST PANDA ROC AUC 95.6 #2 of 12 Archive leaderboard report
Anomaly Detection Fashion-MNIST Self-Supervised One-class SVM, RBF kernel ROC AUC 92.8 #6 of 12 Archive leaderboard report
Anomaly Detection Fashion-MNIST PANDA-OE ROC AUC 91.8 #10 of 12 Archive leaderboard report
Anomaly Detection Fashion-MNIST Self-Supervised DeepSVDD ROC AUC 84.8 #11 of 12 Archive leaderboard report
Anomaly Detection Hyper-Kvasir Dataset PANDA AUC 0.937 #3 of 6 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 PANDA-OE AUROC 98.9 #5 of 36 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 PANDA AUROC 96.2 #11 of 36 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 Self-Supervised DeepSVDD AUROC 64.8 #35 of 36 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 Self-Supervised One-class SVM, RBF kernel AUROC 64.7 #36 of 36 Archive leaderboard report
Anomaly Detection One-class CIFAR-100 PANDA-OE AUROC 97.3 #3 of 15 Archive leaderboard report
Anomaly Detection One-class CIFAR-100 PANDA AUROC 94.1 #5 of 15 Archive leaderboard report
Anomaly Detection One-class CIFAR-100 Self-Supervised Multi-Head RotNet AUROC 80.1 #12 of 15 Archive leaderboard report
Anomaly Detection One-class CIFAR-100 Self-Supervised DeepSVDD AUROC 67 #14 of 15 Archive leaderboard report
Anomaly Detection One-class CIFAR-100 Self-Supervised One-class SVM, RBF kernel AUROC 62.6 #15 of 15 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

Early Stopping

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