arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08658cs.CV
收藏

ESL:语义分割领域自适应的熵引导自监督学习

ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation

Sorbonne University(索邦大学)

Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

摘要:

虽然全监督深度学习为城市场景语义分割提供了良好的模型,但这些模型很难推广到具有不同照明或天气条件的新环境。此外,生成任务所需的大量像素级注释的成本很高。无监督领域自适应(UDA)是一种尝试解决这些问题的方法,以使这样的系统更具可扩展性。特别是,自监督学习(SSL)最近已成为一个有效的策略,UDA在语义分割。这种方法的核心是“伪标签”,即为目标数据分配高置信度类别预测作为伪标签,随后用作真标签的做法。为了收集伪标签,以前的作品通常依赖于最高的softmax分数,我们在这里认为这是一个不利的置信度测量。在这项工作中,我们提出了熵引导的自监督学习(ESL),利用熵作为置信度指标,以产生更准确的伪标签。在不同的UDA基准测试中,ESL始终优于强大的SSL基线,并实现了最先进的结果。

英文摘要:

While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the extensive pixel-level annotations that the task requires comes at a great cost. Unsupervised domain adaptation (UDA) is one approach that tries to address these issues in order to make such systems more scalable. In particular, self-supervised learning (SSL) has recently become an effective strategy for UDA in semantic segmentation. At the core of such methods lies `pseudo-labeling', that is, the practice of assigning high-confident class predictions as pseudo-labels, subsequently used as true labels, for target data. To collect pseudo-labels, previous works often rely on the highest softmax score, which we here argue as an unfavorable confidence measurement. In this work, we propose Entropy-guided Self-supervised Learning (ESL), leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. On different UDA benchmarks, ESL consistently outperforms strong SSL baselines and achieves state-of-the-art results.

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。

↑