Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with Point Supervision via Active Selection

TL;DR

This paper introduces a novel active point annotation method for cross-domain semantic segmentation, improving adaptation efficiency by selecting uncertain target points for minimal supervision.

Contribution

It proposes a new framework combining unsupervised domain adaptation with active point selection based on entropy, enhancing segmentation performance with limited annotations.

Findings

Outperforms existing unsupervised domain adaptation methods.

Effective in reducing annotation effort while maintaining high accuracy.

Framework is compatible with existing adaptation strategies.

Abstract

Training models dedicated to semantic segmentation requires a large amount of pixel-wise annotated data. Due to their costly nature, these annotations might not be available for the task at hand. To alleviate this problem, unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data. While these strategies lead to noticeable improvements, their effectiveness remains limited. To guide the domain adaptation task more efficiently, previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data. In this work, we propose a new domain adaptation framework for semantic segmentation with annotated points via active selection. First, we conduct an unsupervised domain adaptation of the model; from this adaptation, we use an entropy-based uncertainty measurement for target points selection. Finally, to minimize the domain gap, we propose a domain adaptation framework utilizing these target points annotated by human annotators. Experimental results on benchmark datasets show the effectiveness of our methods against existing unsupervised domain adaptation approaches. The propose pipeline is generic and can be included as an extra module to existing domain adaptation strategies.