Union-set Multi-source Model Adaptation for Semantic Segmentation

TL;DR

This paper introduces a novel approach for multi-source model adaptation in semantic segmentation, leveraging model-invariant feature learning to improve generalization across diverse source domains with subset label spaces.

Contribution

It proposes a new union-set multi-source adaptation framework and a model-invariant feature learning strategy to enhance domain adaptation performance.

Findings

Outperforms existing methods in various adaptation settings.

Effectively handles label space subset relations.

Demonstrates superior generalization in target domain.

Abstract

This paper solves a generalized version of the problem of multi-source model adaptation for semantic segmentation. Model adaptation is proposed as a new domain adaptation problem which requires access to a pre-trained model instead of data for the source domain. A general multi-source setting of model adaptation assumes strictly that each source domain shares a common label space with the target domain. As a relaxation, we allow the label space of each source domain to be a subset of that of the target domain and require the union of the source-domain label spaces to be equal to the target-domain label space. For the new setting named union-set multi-source model adaptation, we propose a method with a novel learning strategy named model-invariant feature learning, which takes full advantage of the diverse characteristics of the source-domain models, thereby improving the generalization in the target domain. We conduct extensive experiments in various adaptation settings to show the superiority of our method. The code is available at https://github.com/lzy7976/union-set-model-adaptation.