Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
arXiv:2112.00295
Abstract
This paper challenges the cross-domain semantic segmentation task, aiming to improve the segmentation accuracy on the unlabeled target domain without incurring additional annotation. Using the pseudo-label-based unsupervised domain adaptation (UDA) pipeline, we propose a novel and effective Multiple Fusion Adaptation (MFA) method. MFA basically considers three parallel information fusion strategies, i.e., the cross-model fusion, temporal fusion and a novel online-offline pseudo label fusion. Specifically, the online-offline pseudo label fusion encourages the adaptive training to pay additional attention to difficult regions that are easily ignored by offline pseudo labels, therefore retaining more informative details. While the other two fusion strategies may look standard, MFA pays significant efforts to raise the efficiency and effectiveness for integration, and succeeds in injecting all the three strategies into a unified framework. Experiments on two widely used benchmarks, i.e., GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes, show that our method significantly improves the semantic segmentation adaptation, and sets up new state of the art (58.2% and 62.5% mIoU, respectively). The code will be available at https://github.com/KaiiZhang/MFA.
arXiv comment13 pages, 2 figures, submitted to BMVC2021
References in corpus (4)
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- How does Disagreement Help Generalization against Label Corruption?
- Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation