Corpus ID: 54558282

Deep Anomaly Detection with Outlier Exposure

@article{Hendrycks2019DeepAD,
  title={Deep Anomaly Detection with Outlier Exposure},
  author={Dan Hendrycks and Mantas Mazeika and Thomas G. Dietterich},
  journal={ArXiv},
  year={2019},
  volume={abs/1812.04606}
}
It is important to detect anomalous inputs when deploying machine learning systems. [...] Key Method This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small- and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this…Expand
291 Citations
Deep Anomaly Detection by Residual Adaptation
  • Highly Influenced
  • PDF
Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs
  • Highly Influenced
  • PDF
Unsupervised Learning of Multi-level Structures for Anomaly Detection
  • Songmin Dai, Jide Li, Lu Wang, Congcong Zhu, Yifan Wu, Xiaoqiang Li
  • Computer Science
  • ArXiv
  • 2021
  • PDF
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
  • 1
  • Highly Influenced
  • PDF
Deep Semi-Supervised Anomaly Detection
  • 71
  • PDF
MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
  • 98
  • PDF
Anomalous Instance Detection in Deep Learning: A Survey
  • 15
  • PDF
Robust Out-of-distribution Detection via Informative Outlier Mining
  • 3
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
  • 343
  • PDF
Learning Confidence for Out-of-Distribution Detection in Neural Networks
  • 204
  • Highly Influential
  • PDF
Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
  • 310
  • Highly Influential
  • PDF
Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
  • 469
  • PDF
Systematic construction of anomaly detection benchmarks from real data
  • 121
  • PDF
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
  • 698
  • Highly Influential
  • PDF
On Calibration of Modern Neural Networks
  • 1,272
  • Highly Influential
  • PDF
Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
  • 66
Visualizing and Understanding Convolutional Networks
  • 9,472
  • PDF
Exploring the Limits of Weakly Supervised Pretraining
  • 530
  • PDF
...
1
2
3
4
5
...