Unsupervised Model Adaptation for Continual Semantic Segmentation

TL;DR

This paper introduces an unsupervised model adaptation algorithm for semantic segmentation that aligns target domain data with a source domain prototype in an embedding space, enabling adaptation without source data access.

Contribution

It proposes a novel source-free adaptation method using prototypical distributions in an embedding space, extending UDA techniques to scenarios without source data.

Findings

Achieves competitive performance on benchmark adaptation tasks.

Provides theoretical analysis of the proposed method.

Enables source-free domain adaptation for semantic segmentation.

Abstract

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.