Learning to Adapt Structured Output Space for Semantic Segmentation

TL;DR

This paper introduces an adversarial domain adaptation method for semantic segmentation that leverages structured output space and multi-level adversarial networks to improve generalization across different image domains.

Contribution

It proposes a novel adversarial learning framework that adapts semantic segmentation models to new domains by focusing on output space and multi-level feature alignment.

Findings

Outperforms state-of-the-art methods in accuracy

Effective in synthetic-to-real and cross-city scenarios

Improves visual quality of segmentation results

Abstract

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest. In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation. Considering semantic segmentations as structured outputs that contain spatial similarities between the source and target domains, we adopt adversarial learning in the output space. To further enhance the adapted model, we construct a multi-level adversarial network to effectively perform output space domain adaptation at different feature levels. Extensive experiments and ablation study are conducted under various domain adaptation settings, including synthetic-to-real and cross-city scenarios. We show that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.