arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09779cs.CV
收藏

面向领域自适应语义分割的双向领域混合算法

Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

Hanbat National University(韩巴国立大学);SI Analytics;Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

Daehan Kim, Minseok Seo, Kwanyong Park, Inkyu Shin, Sanghyun Woo, In-So Kweon, Dong-Geol Choi

摘要:

Mixup提供插值训练样本,并允许模型获得更平滑的决策边界,以实现更好的泛化。该思想可以自然地应用于领域自适应任务,在该任务中,我们可以混合源样本和目标样本以获得领域混合样本以用于更好的自适应。然而,从分类到分割的思想的扩展(即,结构化输出)是不平凡的。本文系统地研究了领域自适应语义分割任务中混淆的影响,提出了一种简单有效的混淆策略--双向领域混淆(BDM)。具体来说,我们通过两步实现了域混合:剪贴。给定从任何自适应技术训练的预热模型,我们转发源样本和目标样本,并执行简单的基于阈值的不自信区域(切割)。然后,我们用其他域区域补丁(粘贴)填充丢弃的区域。在这样做时,我们共同考虑类分布,空间结构和伪标签置信度。基于我们的分析,我们发现BDM通过剪切留下域可转移区域,通过粘贴平衡了类集级的类分布,同时保留了自然场景上下文。我们将我们的建议与各种最先进的适应模型相结合,并持续观察到显着的改善。我们还提供了广泛的消融实验,以经验验证我们的框架的主要组成部分。访问我们的项目页面,代码在https://sites.google.com/view/bidirectional-domain-mixup

英文摘要:

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the source and target samples to obtain domain-mixed samples for better adaptation. However, the extension of the idea from classification to segmentation (i.e., structured output) is nontrivial. This paper systematically studies the impact of mixup under the domain adaptaive semantic segmentation task and presents a simple yet effective mixup strategy called Bidirectional Domain Mixup (BDM). In specific, we achieve domain mixup in two-step: cut and paste. Given the warm-up model trained from any adaptation techniques, we forward the source and target samples and perform a simple threshold-based cut out of the unconfident regions (cut). After then, we fill-in the dropped regions with the other domain region patches (paste). In doing so, we jointly consider class distribution, spatial structure, and pseudo label confidence. Based on our analysis, we found that BDM leaves domain transferable regions by cutting, balances the dataset-level class distribution while preserving natural scene context by pasting. We coupled our proposal with various state-of-the-art adaptation models and observe significant improvement consistently. We also provide extensive ablation experiments to empirically verify our main components of the framework. Visit our project page with the code at https://sites.google.com/view/bidirectional-domain-mixup

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。

↑