对比了主流无监督域适应算法在图像分类中的表现与局限。
Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification
- 通过仿真测试多种无监督域适应方法，评估其跨域泛化能力。
- SSRT在Office-31上达91.6%准确率，但受限于批大小时在Office-Home降至72.4%。
- 适合关注域适应性能边界与实际部署挑战的研究者参考。
传统机器学习假设训练集与测试集来自同一分布，但在实际应用中这一假设常不成立，导致模型在新数据上性能严重下降。域适应（DA）旨在通过缩小不同数据域间的差异来缓解此问题。本文基于仿真，实现并比较了近期主流的无监督域适应（UDA）技术，其中仅源域提供标签。实验在多个公开数据集及不同特性下进行，揭示了各类方法的优势与缺陷。例如，基于Transformer的稳健自精炼方法（SSRT）在Office-31数据集上达到最高准确率91.6%，但在使用小批量时于Office-Home数据集上准确率下降至72.4%。本研究不仅增进对当前DA技术的理解，也指出了该领域面临的挑战与未来方向。代码已开源：https://github.com/AIPMLab/Domain_Adaptation。
原文摘要 · Abstract (English)
Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance drops when the trained model is used in new data sets. Domain adaptation (DA) is a machine learning technique that aims to address this problem by reducing the differences between domains. This paper presents simulation-based algorithms of recent DA techniques, mainly related to unsupervised domain adaptation (UDA), where labels are available only in the source domain. Our study compares these techniques with public data sets and diverse characteristics, highlighting their respective strengths and drawbacks. For example, Safe Self-Refinement for Transformer-based DA (SSRT) achieved the highest accuracy (91.6\%) in the office-31 data set during our simulations, however, the accuracy dropped to 72.4\% in the Office-Home data set when using limited batch sizes. In addition to improving the reader's comprehension of recent techniques in DA, our study also highlights challenges and upcoming directions for research in this domain. The codes are available at https://github.com/AIPMLab/Domain_Adaptation.
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。