【论文总结】 Multi-source Domain Adaptation (持续更新)

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

---

Single-source DA vs Multi-source DA

SUDA

• labeled data is from one single source domain
• 常用solution: learn to map the data from source & target domains into a common feature space to learn domain-invariant representations by minimizing domain distribution discrepancy (MMD/)

MUDA

• shift between multiple source domains (hard to align)
• 有时候 domain 之间拥有的 class 范围甚至不同
• 在domain-specific decision boundary 附近的 target samples 可能会被不同的classifier 判别出不同的labels
• 常用sol：two-stage alignments
  – stage I: map each pair of source and target domains data into multiple different feature spaces --> align domain-specific distributions to learn multiple domain-invariant representations --> train multiple domain-specific classifiers using multiple domains-invariant representations
  – stage II: aligning domain-specific classifiers
  

---

Paper I: Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources (AAAI’19)

---

Problem Formulation

Given

• $N$ different underlying source distributions { p s j ( x , y ) } j = 1 N \{p_{sj}(x,y)\}_{j=1}^{N} { psj​(x,y)}j=1N​ and labeled source domain data $\{(X_{sj},Y_{sj}){\}}_{j=1}^N$ drawn from these distributions
• target distribution { p t ( x , y ) } \{p_{t}(x,y)\} { pt​(x,y)} , from which target domain data $X_t$ are sampled yet without label observation $Y_t$ .

Objective

---

Methodology

Two-stage alignment Framework

Common feature extractor

A common subnetwork f ( . ) f(.)