提出新型度量方法，让模型在跨域适应中同时优化分布对齐与分类边界。
Decision Boundary Optimization-Informed Domain Adaptation
- 引入决策边界感知的MMD，融合分布对齐与分类优化
- 在8个标准数据集上提升基线模型性能，最高达9.5%准确率增益
- 可无缝嵌入主流方法，适合关注跨域泛化性能的研究者
最大均值差异（MMD）广泛应用于领域自适应（DA）方法中，有效对齐跨域数据分布。然而，以往基于MMD的DA方法多聚焦于分布对齐，忽视了对分类任务关键的决策边界优化，导致无法有效降低领域自适应的理论误差上界。本文提出一种增强型MMD度量——决策边界优化感知的MMD（DB-MMD），使MMD能够精细考虑决策边界，从而在混合框架下同步优化分布对齐与跨域分类器，实现理论误差上界指导的自适应学习。我们进一步将该度量无缝嵌入MEDA、DGA-DA等主流方法，在8个标准领域自适应数据集上进行综合实验。结果表明，采用DB-MMD的算法相比使用普通MMD的基线模型，性能提升最高可达9.5个百分点。
原文摘要 · Abstract (English)
Maximum Mean Discrepancy (MMD) is widely used in a number of domain adaptation (DA) methods and shows its effectiveness in aligning data distributions across domains. However, in previous DA research, MMD-based DA methods focus mostly on distribution alignment, and ignore to optimize the decision boundary for classification-aware DA, thereby falling short in reducing the DA upper error bound. In this paper, we propose a strengthened MMD measurement, namely, Decision Boundary optimization-informed MMD (DB-MMD), which enables MMD to carefully take into account the decision boundaries, thereby simultaneously optimizing the distribution alignment and cross-domain classifier within a hybrid framework, and leading to a theoretical bound guided DA. We further seamlessly embed the proposed DB-MMD measurement into several popular DA methods, e.g., MEDA, DGA-DA, to demonstrate its effectiveness w.r.t different experimental settings. We carry out comprehensive experiments using 8 standard DA datasets. The experimental results show that the DB-MMD enforced DA methods improve their baseline models using plain vanilla MMD, with a margin that can be as high as 9.5.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。