Principled Detection of Out-of-Distribution Examples in Neural Networks

We consider the problem of detecting out-of-distribution examples in neural networks. We propose ODIN, a simple and effective out-of-distribution detector for neural networks, that does not require any change to a pre-trained model. Our method is based on the observation that using temperature scaling and adding small perturbations to the input can separate the softmax score distributions of inand out-of-distribution samples, allowing for more effective detection. We show in a series of experiments that our approach is compatible with diverse network architectures and datasets. It consistently outperforms the baseline approach [1] by a large margin, establishing a new state-of-the-art performance on this task. For example, ODIN reduces the false positive rate from the baseline 34.7% to 4.3% on the DenseNet (applied to CIFAR-10) when the true positive rate is 95%. We theoretically analyze the method and prove that performance improvement is guaranteed under mild conditions on the image distributions.

[1]  P. Kantor.  Foundations of Statistical Natural Language Processing , 2001, Information Retrieval.

[2]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[3]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[4]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[5]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[7]  L. Deng,et al.  Calibration of Confidence Measures in Speech Recognition , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[8]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Geoffrey E. Hinton,et al.  Acoustic Modeling Using Deep Belief Networks , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[14]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[16]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[17]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[18]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[19]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[20]  Pingmei Xu,et al.  TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking , 2015, ArXiv.

[21]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Yinda Zhang,et al.  LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop , 2015, ArXiv.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[25]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[26]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[27]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  John Schulman,et al.  Concrete Problems in AI Safety , 2016, ArXiv.

[29]  Seyed-Mohsen Moosavi-Dezfooli,et al.  Universal Adversarial Perturbations , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[31]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Geoffrey E. Hinton,et al.  Regularizing Neural Networks by Penalizing Confident Output Distributions , 2017, ICLR.

[33]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[34]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.