Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift

05/31/2021
by   Sebastian Cygert, et al.
21

While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It was shown that simple color transformations already provide a strong baseline, comparable to using more sophisticated style-transfer data augmentation. Further, by constructing an ensemble consisting of models using different backbones and/or augmentation methods, it was possible to improve significantly model performance in terms of overall accuracy and uncertainty estimation under the domain shift setting. The Expected Calibration Error (ECE) on challenging GTA to Cityscapes adaptation was reduced from 4.05 to the competitive value of 1.1. Further, an ensemble of models was utilized in the self-training setting to improve the pseudo-labels generation, which resulted in a significant gain in the final model accuracy, compared to the standard fine-tuning (without ensemble).

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

research
04/30/2021

Self-supervised Augmentation Consistency for Adapting Semantic Segmentation

We propose an approach to domain adaptation for semantic segmentation th...
research
08/02/2021

Reliable Semantic Segmentation with Superpixel-Mix

Along with predictive performance and runtime speed, reliability is a ke...
research
03/08/2020

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

This paper focuses on the unsupervised domain adaptation of transferring...
research
08/12/2022

Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer

In recent years, there has been tremendous progress in the field of sema...
research
08/19/2023

Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation

Within the context of autonomous driving, encountering unknown objects b...
research
03/20/2023

Reliability in Semantic Segmentation: Are We on the Right Track?

Motivated by the increasing popularity of transformers in computer visio...
research
06/09/2022

BSM loss: A superior way in modeling aleatory uncertainty of fine_grained classification

Artificial intelligence(AI)-assisted method had received much attention ...

Please sign up or login with your details

Forgot password? Click here to reset