English

Domain Adaptation Using Pseudo Labels

Computer Vision and Pattern Recognition 2024-03-13 v3

Abstract

In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment procedures are category-agnostic and end up misaligning the categories. We address this problem by deploying a pretrained network to determine accurate labels for the target domain using a multi-stage pseudo-label refinement procedure. The filters are based on the confidence, distance (conformity), and consistency of the pseudo labels. Our results on multiple datasets demonstrate the effectiveness of our simple procedure in comparison with complex state-of-the-art techniques.

Keywords

Cite

@article{arxiv.2402.06809,
  title  = {Domain Adaptation Using Pseudo Labels},
  author = {Sachin Chhabra and Hemanth Venkateswara and Baoxin Li},
  journal= {arXiv preprint arXiv:2402.06809},
  year   = {2024}
}

Comments

8 pages + 3 pages of references

R2 v1 2026-06-28T14:44:40.772Z