• Corpus ID: 252918149

Self-supervision is not magic: Understanding Data Augmentation in Image Anomaly Detection

@inproceedings{Yoo2022SelfsupervisionIN,
  title={Self-supervision is not magic: Understanding Data Augmentation in Image Anomaly Detection},
  author={Jaemin Yoo and Tianchen Zhao and Leman Akoglu},
  year={2022}
}
Self-supervised learning (SSL) has emerged as a promising alternative to create supervisory signals to real-world tasks, avoiding the extensive cost of labeling. SSL is particularly attractive for unsupervised tasks such as anomaly detection (AD), where labeled anomalies are costly to secure, difficult to simulate, or even nonexistent. A large catalog of augmentation functions have been used for SSL-based AD (SSAD) on image data, and recent works have observed that the type of augmentation has a… 

References

SHOWING 1-10 OF 37 REFERENCES

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

This work proposes a two-stage framework for building anomaly detectors using normal training data only, which first learns self-supervised deep representations and then builds a generative one-class classifier on learned representations.

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

This work introduces a novel anomaly detection model, by using a conditional generative adversarial network that jointly learns the generation of high-dimensional image space and the inference of latent space and shows the model efficacy and superiority over previous state-of-the-art approaches.

Attribute Restoration Framework for Anomaly Detection

This work proposes to break information equivalence among input and supervision for reconstruction tasks by erasing selected attributes from the original data and reformulate it as a restoration task, where the normal and the anomalous data are expected to be distinguishable based on restoration errors.

Adversarially Learned Anomaly Detection

This work proposes an anomaly detection method, Adversarially Learned Anomaly Detection (ALAD), that derives adversarially learned features for the anomaly detection task that achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.

Deep Semi-Supervised Anomaly Detection

This work presents Deep SAD, an end-to-end deep methodology for general semi-supervised anomaly detection, and introduces an information-theoretic framework for deep anomaly detection based on the idea that the entropy of the latent distribution for normal data should be lower than the entropy the anomalous distribution, which can serve as a theoretical interpretation for the method.

CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows

A real-time model based on a conditional normalizing flow frame- work adopted for anomaly detection with localization that is faster and smaller by a factor of 10× than prior state-of-the-art with the same input setting and outperforms previous methods.

Self-supervised Pretraining of Visual Features in the Wild

The final SElf-supERvised (SEER) model, a RegNetY with 1.3B parameters trained on 1B random images with 512 GPUs achieves 84.2% top-1 accuracy, surpassing the best self-supervised pretrained model by 1% and confirming that self- Supervised learning works in a real world setting.

Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection*

This paper proposes a novel approach that learns disentangled representations of abnormalities illustrated by seen anomalies, pseudo anomalies, and latent residual anomalies (i.e., samples that have unusual residuals compared to the normal data in a latent space), with the last two abnormalities designed to detect unseen anomalies.

Understanding the Effect of Bias in Deep Anomaly Detection

The first finite sample rates for estimating the relative scoring bias for deep anomaly detection, and empirically validate the theoretical results on both synthetic and real-world datasets are established.

Deep One-Class Classification

This paper introduces a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective and shows the effectiveness of the method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GTSRB stop signs.