Corpus ID: 13046179

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

@article{Hendrycks2017ABF,
  title={A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks},
  author={Dan Hendrycks and Kevin Gimpel},
  journal={ArXiv},
  year={2017},
  volume={abs/1610.02136}
}
We consider the two related problems of detecting if an example is misclassified or out-of-distribution. [...] Key Result We then show the baseline can sometimes be surpassed, demonstrating the room for future research on these underexplored detection tasks.Expand
762 Citations

Paper Mentions

Principled Detection of Out-of-Distribution Examples in Neural Networks
Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
OUT-OF-DISTRIBUTION DETECTION USING DEEP NEURAL NETWORKS
  • 2019
Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
Out-of-distribution Detection in Classifiers via Generation
Contrastive Training for Improved Out-of-Distribution Detection
Likelihood Ratios for Out-of-Distribution Detection
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Learning Multiple Layers of Features from Tiny Images
Calibration of Confidence Measures in Speech Recognition
  • Dong Yu, J. Li, Li Deng
  • Mathematics
  • IEEE Transactions on Audio, Speech, and Language Processing
  • 2011
The Case against Accuracy Estimation for Comparing Induction Algorithms
Unsupervised Risk Estimation Using Only Conditional Independence Structure
Posterior calibration and exploratory analysis for natural language processing models
Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets
Explaining and Harnessing Adversarial Examples
...
1
2
3
4
5
...