Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output

Published in

arXiv.org(2019)

External Links:

Generate Graph

TL;DR

This paper proposes a new OOD detection approach that can be easily applied to an existing classifier and does not need to have access to OOD samples, and achieves substantially better results over multiple metrics.

Abstract

Deep neural networks achieve superior performance in challenging tasks such as image classification. However, deep classifiers tend to incorrectly classify out-of-distribution (OOD) inputs, which are inputs that do not belong to the classifier training distribution. Several approaches have been proposed to detect OOD inputs, but the detection task is still an ongoing challenge. In this paper, we propose a new OOD detection approach that can be easily applied to an existing classifier and does not need to have access to OOD samples. The detector is a one-class classifier trained on the output of an early layer of the original classifier fed with its original training set. We apply our approach to several low- and high-dimensional datasets and compare it to the state-of-the-art detection approaches. Our approach achieves substantially better results over multiple metrics.

Authors

K. Czarnecki

4 papers

Vahdat Abdelzad

1 papers

Rick Salay

1 papers

References39 items

Likelihood Ratios for Out-of-Distribution Detection

Analysis of Confident-Classifiers for Out-of-distribution Detection

Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem

Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance

Do Deep Generative Models Know What They Don't Know?

Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output

Published in

arXiv.org(2019)

External Links:

Generate Graph

TL;DR

Abstract

Authors

K. Czarnecki

4 papers

Vahdat Abdelzad

1 papers

Rick Salay

1 papers

References39 items

Likelihood Ratios for Out-of-Distribution Detection

Analysis of Confident-Classifiers for Out-of-distribution Detection

Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problem

Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance

Do Deep Generative Models Know What They Don't Know?

Taylor Denouden

1 papers

Sachin Vernekar

1 papers

Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers

UMAP: Uniform Manifold Approximation and Projection

Out-of-Distribution Detection using Multiple Semantic Label Representations

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Generative Probabilistic Novelty Detection with Adversarial Autoencoders

Learning Confidence for Out-of-Distribution Detection in Neural Networks

Learning Deep Features for One-Class Classification

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

Safer Classification by Synthesis

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

On Calibration of Modern Neural Networks

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

Selective Classification for Deep Neural Networks

Deep Bayesian Active Learning with Image Data

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis

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

WaveNet: A Generative Model for Raw Audio

Human-level concept learning through probabilistic program induction

Deep Residual Learning for Image Recognition

LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Very Deep Convolutional Networks for Large-Scale Image Recognition

One-class classification: taxonomy of study and review of techniques

ImageNet classification with deep convolutional neural networks

Anomaly detection: A survey

ImageNet: A large-scale hierarchical image database

Active Hidden Markov Models for Information Extraction

Support vector domain description

Review: A review of novelty detection. Signal Process

Reading Digits in Natural Images with Unsupervised Feature Learning

Learning Multiple Layers of Features from Tiny Images

A Mathematical Theory of Communication

Field of Study

Computer ScienceMathematics

Journal Information

Name

ArXiv

Volume

abs/2005.00687

Venue Information

Name

arXiv.org

Type

URL

https://arxiv.org

Alternate Names

ArXiv