Semi-supervised Anomaly Detection
28 papers with code • 1 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Semi-supervised Anomaly Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Semi-supervised Anomaly Detection models and implementations
MVTec LOCO AD
UBI-Fights
Most implemented papers
Unseen Anomaly Detection on Networks via Multi-Hypersphere Learning
betterzhou/MHGL
•
•
SIAM International Conference on Data Mining 2022
Network anomaly detection is a crucial task since a few anomalies can cause huge losses.
R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Neural networks follow a gradient-based learning scheme, adapting their mapping parameters by back-propagating the output loss.
SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs
d10andy/sad
•
•
Anomaly detection aims to distinguish abnormal instances that deviate significantly from the majority of benign ones.
On Diffusion Modeling for Anomaly Detection
vicliv/dte
•
•
By simplifying DDPM in application to anomaly detection, we are naturally led to an alternative approach called Diffusion Time Estimation (DTE).
AnoOnly: Semi-Supervised Anomaly Detection with the Only Loss on Anomalies
Unlike existing SSAD methods that resort to strict loss supervision, AnoOnly suspends it and introduces a form of weak supervision for normal data.
RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervision
xuhongzuo/rosas
•
•
anomaly contamination.
ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition
cool-xuan/imbalanced_sam
•
•
ICCV 2023
To overcome this bottleneck, we leverage class priors to restrict the generalization scope of the class-agnostic SAM and propose a class-aware smoothness optimization algorithm named Imbalanced-SAM (ImbSAM).
NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation
While AD is typically treated as an unsupervised learning task due to the high cost of label annotation, it is more practical to assume access to a small set of labeled anomaly samples from domain experts, as is the case for semi-supervised anomaly detection.
