681 papers with code • 36 benchmarks • 55 datasets
Humans are able to detect heterogeneous or unexpected patterns in a set of homogeneous natural images. This task is known as anomaly or novelty detection and has a large number of applications. Anomaly detection automation would enable constant quality control by avoiding reduced attention span and facilitating human operator work.
Anomaly detection is a binary classification between the normal and the anomalous classes. However, it is not possible to train a model with full supervision for this task because we frequently lack anomalous examples, and, what is more, anomalies can have unexpected patterns.
[Image source]: GAN-based Anomaly Detection in Imbalance Problems
- Unsupervised Anomaly Detection
- Anomaly Detection In Surveillance Videos
- Abnormal Event Detection In Video
- Few Shot Anomaly Detection
- Few Shot Anomaly Detection
- Self-Supervised Anomaly Detection
- Group Anomaly Detection
- Contextual Anomaly Detection
- 3D Anomaly Detection and Segmentation
- Depth Anomaly Detection and Segmentation
- RGB+Depth Anomaly Detection and Segmentation
- RGB+3D Anomaly Detection and Segmentation
- Unsupervised Anomaly Detection In Sound
- 3D Anomaly Detection
- 3D Anomaly Segmentation
- Depth Anomaly Segmentation
- 3D + RGB Anomaly Segmentation
- Depth + RGB Anomaly Segmentation
- Depth + RGB Anomaly Detection
- 3D + RGB Anomaly Detection
- DepthAnomaly Detection
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging.
We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting.
We consider the two related problems of detecting if an example is misclassified or out-of-distribution.
To evaluate models robustly and to get an estimate of radiologist performance, we collect additional labels from six board-certified Stanford radiologists on the test set, consisting of 207 musculoskeletal studies.
To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e. g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation.
Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal).
To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i. e. the training labels (anomalous or normal) are at video-level instead of clip-level.