Domain Adaptations for Computer Vision Applications
Oscar Beijbom, Department of Computer Science and Engineering, University of California, San Diego
Abstract
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn’t hold in many applications. Instead, ample labeled data might exist in a particular ‘source’ domain while inference is needed in another, ‘target’ domain. Domain adaptation methods leverage labeled data from both domains to improve classification on unseen data in the target domain. In this work we survey domain transfer learning methods for various application domains with focus on recent work in Computer Vision.
中文速览
当训练数据和实际测试数据来自不同分布、目标领域又缺少标注时，如何借助源领域的丰富标注数据做好目标领域分类，是领域自适应要解决的问题。文章系统梳理了这一方向，按思路归纳为给源样本加权、用源领域模型约束目标模型，以及学习能对齐源域和目标域的共同特征表示，并区分了监督、半监督和无监督等设置。已有方法分别利用类别比例或特征分布差异修正训练权重，或通过贝叶斯先验、支持向量机等方式迁移源领域知识，覆盖计算机视觉、自然语言处理、语音等应用。这个综述的重要性在于厘清了领域自适应与迁移学习、协变量偏移等相关概念，为标注昂贵、数据分布不断变化的实际任务提供了方法地图。
原文 arXiv:1211.4860;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1211.4860v1