Dense open-set recognition with synthetic outliers generated by Real NVP

11/22/2020
by   Matej Grcić, et al.
0

Today's deep models are often unable to detect inputs which do not belong to the training distribution. This gives rise to confident incorrect predictions which could lead to devastating consequences in many important application fields such as healthcare and autonomous driving. Interestingly, both discriminative and generative models appear to be equally affected. Consequently, this vulnerability represents an important research challenge. We consider an outlier detection approach based on discriminative training with jointly learned synthetic outliers. We obtain the synthetic outliers by sampling an RNVP model which is jointly trained to generate datapoints at the border of the training distribution. We show that this approach can be adapted for simultaneous semantic segmentation and dense outlier detection. We present image classification experiments on CIFAR-10, as well as semantic segmentation experiments on three existing datasets (StreetHazards, WD-Pascal, Fishyscapes Lost Found), and one contributed dataset. Our models perform competitively with respect to the state of the art despite producing predictions with only one forward pass.

READ FULL TEXT

page 7

page 8

research
08/03/2019

Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift

Recent success on realistic road driving datasets has increased interest...
research
01/22/2021

Dense outlier detection and open-set recognition based on training with noisy negative images

Deep convolutional models often produce inadequate predictions for input...
research
12/23/2021

Dense anomaly detection by robust learning on synthetic negative data

Standard machine learning is unable to accommodate inputs which do not b...
research
03/23/2021

Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs

Deep neural networks (DNNs) are known to produce incorrect predictions w...
research
08/23/2018

Discriminative out-of-distribution detection for semantic segmentation

This paper considers dense detection of out-of-distribution pixels. As a...
research
01/19/2023

Hybrid Open-set Segmentation with Synthetic Negative Data

Open-set segmentation is often conceived by complementing closed-set cla...
research
07/06/2022

DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition

Anomaly detection can be conceived either through generative modelling o...

Please sign up or login with your details

Forgot password? Click here to reset