Timezone: »

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
Kendrick Shen · Robbie Jones · Ananya Kumar · Sang Michael Xie · Jeff Z. HaoChen · Tengyu Ma · Percy Liang

Thu Jul 21 11:05 AM -- 11:25 AM (PDT) @ Ballroom 1 & 2

We consider unsupervised domain adaptation (UDA), where labeled data from a source domain (e.g., photos) and unlabeled data from a target domain (e.g., sketches) are used to learn a classifier for the target domain. Conventional UDA methods (e.g., domain adversarial training) learn domain-invariant features to generalize from the source domain to the target domain. In this paper, we show that contrastive pre-training, which learns features on unlabeled source and target data and then fine-tunes on labeled source data, is competitive with strong UDA methods. However, we find that contrastive pre-training does not learn domain-invariant features, diverging from conventional UDA intuitions. We show theoretically that contrastive pre-training can learn features that vary subtantially across domains but still generalize to the target domain, by disentangling domain and class information. We empirically validate our theory on benchmark vision datasets.

Author Information

Kendrick Shen (Stanford University)
Robbie Jones (Stanford University)
Ananya Kumar (Stanford University)
Sang Michael Xie (Stanford University)
Jeff Z. HaoChen (Stanford University)
Tengyu Ma (Stanford University)
Percy Liang (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors