Domain adaptation for object recognition: An unsupervised approach

  title={Domain adaptation for object recognition: An unsupervised approach},
  author={Raghuraman Gopalan and Ruonan Li and Rama Chellappa},
  journal={2011 International Conference on Computer Vision},
Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not have correspondences between object categories across domains). Motivated by incremental learning, we create intermediate representations of… CONTINUE READING
Highly Influential
This paper has highly influenced 107 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 739 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 447 extracted citations

739 Citations

Citations per Year
Semantic Scholar estimates that this publication has 739 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 43 references

Manifold alignment without correspondence

  • C. Wang, S. Mahadevan
  • In IJCAI,
  • 2009
Highly Influential
4 Excerpts

Partial Least Squares, volume 6

  • H. Wold
  • Encyclopedia of Statistical Sciences,
  • 1985
Highly Influential
7 Excerpts

Riemannian center of mass and mollifier smoothing

  • H. Karcher
  • Communications on Pure and Applied Mathematics,
  • 1977
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…