Unsupervised Model Adaptation for Continual Semantic Segmentation

09/26/2020
by   Serban Stan, et al.
4

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain adaptation (UDA) literature, but existing UDA algorithms require access to both the source domain labeled data and the target domain unlabeled data for training a domain agnostic semantic segmentation model. Relaxing this constraint enables a user to adapt pretrained models to generalize in a target domain, without requiring access to source data. To this end, we learn a prototypical distribution for the source domain in an intermediate embedding space. This distribution encodes the abstract knowledge that is learned from the source domain. We then use this distribution for aligning the target domain distribution with the source domain distribution in the embedding space. We provide theoretical analysis and explain conditions under which our algorithm is effective. Experiments on benchmark adaptation task demonstrate our method achieves competitive performance even compared with joint UDA approaches.

READ FULL TEXT

page 3

page 7

page 12

research
07/01/2020

Sequential Unsupervised Domain Adaptation through Prototypical Distributions

We develop an algorithm for unsupervised domain adaptation (UDA) of a cl...
research
01/27/2023

Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows

In this paper, we propose an unsupervised framework based on normalizing...
research
09/29/2022

Increasing Model Generalizability for Unsupervised Domain Adaptation

A dominant approach for addressing unsupervised domain adaptation is to ...
research
11/02/2022

Unsupervised Model Adaptation for Source-free Segmentation of Medical Images

The recent prevalence of deep neural networks has lead semantic segmenta...
research
03/02/2022

Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation

Environment perception in autonomous driving vehicles often heavily reli...
research
04/05/2021

Unsupervised Multi-source Domain Adaptation Without Access to Source Data

Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for...

Please sign up or login with your details

Forgot password? Click here to reset