arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.03773cs.CV
收藏

基于不确定性估计的领域自适应语义分割伪标签学习校正

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

University of Technology Sydney(悉尼科技大学);Australian Artificial Intelligence Institute (AAII)(澳大利亚人工智能研究所 (AAII))

Zhedong Zheng, Yi Yang

摘要:

本文主要研究在语义分割的背景下,将知识从源领域转移到目标领域的无监督领域自适应。现有的方法通常将伪标签作为基础事实,以充分利用未标记的目标域数据。然而,目标域数据的伪标签通常由在源域上训练的模型预测。因此,由于训练域和测试域之间的差异,生成的标签不可避免地包含不正确的预测,这可能会转移到最终的自适应模型,并在很大程度上损害了训练过程。为了克服这个问题,本文提出在训练过程中显式地估计预测不确定性,以纠正用于无监督语义分割适应的伪标签学习。给定输入图像,模型输出语义分割预测以及预测的不确定性。具体来说,我们通过预测方差对不确定性进行建模,并将不确定性纳入优化目标。为了验证所提出的方法的有效性,我们评估了两个流行的合成到真实的语义分割基准,即,GTA 5-> Cityscapes和SYNTHIA -> Cityscapes,以及一个跨城市基准,即城市景观->牛津机器人汽车。我们通过大量的实验证明,所提出的方法(1)根据预测方差动态设置不同的置信阈值,(2)纠正了从噪声伪标签中学习,(3)实现了对传统伪标签学习的显着改进,并在所有三个基准测试中产生了有竞争力的性能。

英文摘要:

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. Yet the pseudo labels of the target-domain data are usually predicted by the model trained on the source domain. Thus, the generated labels inevitably contain the incorrect prediction due to the discrepancy between the training domain and the test domain, which could be transferred to the final adapted model and largely compromises the training process. To overcome the problem, this paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning for unsupervised semantic segmentation adaptation. Given the input image, the model outputs the semantic segmentation prediction as well as the uncertainty of the prediction. Specifically, we model the uncertainty via the prediction variance and involve the uncertainty into the optimization objective. To verify the effectiveness of the proposed method, we evaluate the proposed method on two prevalent synthetic-to-real semantic segmentation benchmarks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, as well as one cross-city benchmark, i.e., Cityscapes -> Oxford RobotCar. We demonstrate through extensive experiments that the proposed approach (1) dynamically sets different confidence thresholds according to the prediction variance, (2) rectifies the learning from noisy pseudo labels, and (3) achieves significant improvements over the conventional pseudo label learning and yields competitive performance on all three benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑