Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders

05/04/2021
by   Felix Möller, et al.
1

Deep neural networks often suffer from overconfidence which can be partly remedied by improved out-of-distribution detection. For this purpose, we propose a novel approach that allows for the generation of out-of-distribution datasets based on a given in-distribution dataset. This new dataset can then be used to improve out-of-distribution detection for the given dataset and machine learning task at hand. The samples in this dataset are with respect to the feature space close to the in-distribution dataset and therefore realistic and plausible. Hence, this dataset can also be used to safeguard neural networks, i.e., to validate the generalization performance. Our approach first generates suitable representations of an in-distribution dataset using an autoencoder and then transforms them using our novel proposed Soft Brownian Offset method. After transformation, the decoder part of the autoencoder allows for the generation of these implicit out-of-distribution samples. This newly generated dataset then allows for mixing with other datasets and thus improved training of an out-of-distribution classifier, increasing its performance. Experimentally, we show that our approach is promising for time series using synthetic data. Using our new method, we also show in a quantitative case study that we can improve the out-of-distribution detection for the MNIST dataset. Finally, we provide another case study on the synthetic generation of out-of-distribution trajectories, which can be used to validate trajectory prediction algorithms for automated driving.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2019

A synthetic dataset for deep learning

In this paper, we propose a novel method for generating a synthetic data...
research
05/24/2023

Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science

Large Language Models (LLMs) have democratized synthetic data generation...
research
10/09/2019

Out-of-distribution Detection in Classifiers via Generation

By design, discriminatively trained neural network classifiers produce r...
research
07/07/2020

Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks

Soft labeling becomes a common output regularization for generalization ...
research
01/03/2021

Synthetic Embedding-based Data Generation Methods for Student Performance

Given the inherent class imbalance issue within student performance data...
research
07/28/2020

A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories

We propose a unified deep learning framework for generation and analysis...
research
04/01/2022

Autoencoder Attractors for Uncertainty Estimation

The reliability assessment of a machine learning model's prediction is a...

Please sign up or login with your details

Forgot password? Click here to reset