Learning to Adapt Structured Output Space for Semantic Segmentation
This addresses the tedious labeling process for semantic segmentation by enabling adaptation to new domains, but it is incremental as it builds on existing adversarial learning approaches.
The paper tackles the problem of semantic segmentation models failing to generalize to unseen image domains due to reliance on pixel-level ground truth labels, proposing an adversarial learning method for domain adaptation in the output space that achieves favorable performance against state-of-the-art methods in accuracy and visual quality.
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.