False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates

06/28/2021
by   Kira Maag, et al.
0

Instance segmentation of images is an important tool for automated scene understanding. Neural networks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such as automated driving, an overlooked pedestrian seems more harmful than a falsely detected one. In this work, we present a false negative detection method for image sequences based on inconsistencies in time series of tracked instances given the availability of image sequences in online applications. As the number of instances can be greatly increased by this algorithm, we apply a false positive pruning using uncertainty estimates aggregated over instances. To this end, instance-wise metrics are constructed which characterize uncertainty and geometry of a given instance or are predicated on depth estimation. The proposed method serves as a post-processing step applicable to any neural network that can also be trained on single frames only. In our tests, we obtain an improved trade-off between false negative and false positive instances by our fused detection approach in comparison to the use of an ordinary score value provided by the instance segmentation network during inference.

READ FULL TEXT

page 1

page 7

research
12/14/2020

Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates

Instance segmentation with neural networks is an essential task in envir...
research
12/16/2019

MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation

In semantic segmentation datasets, classes of high importance are oftent...
research
02/16/2020

Key Points Estimation and Point Instance Segmentation Approach for Lane Detection

State-of-the-art lane detection methods achieve successful performance. ...
research
07/07/2022

False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation

State-of-the-art deep neural networks demonstrate outstanding performanc...
research
04/30/2019

Detecting Reflections by Combining Semantic and Instance Segmentation

Reflections in natural images commonly cause false positives in automate...
research
12/08/2019

Detection of False Positive and False Negative Samples in Semantic Segmentation

In recent years, deep learning methods have outperformed other methods i...
research
12/10/2018

Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN

PURPOSE: To apply deep convolutional neural networks (CNN) to the left v...

Please sign up or login with your details

Forgot password? Click here to reset