Semi-supervised Domain Adaptation with Instance Constraints

Jeff Donahue, Judy Hoffman, Erik Rodner, Kate Saenko, Trevor Darrell; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 668-675


Most successful object classification and detection methods rely on classifiers trained on large labeled datasets. However, for domains where labels are limited, simply borrowing labeled data from existing datasets can hurt performance, a phenomenon known as "dataset bias." We propose a general framework for adapting classifiers from "borrowed" data to the target domain using a combination of available labeled and unlabeled examples. Specifically, we show that imposing smoothness constraints on the classifier scores over the unlabeled data can lead to improved adaptation results. Such constraints are often available in the form of instance correspondences, e.g. when the same object or individual is observed simultaneously from multiple views, or tracked between video frames. In these cases, the object labels are unknown but can be constrained to be the same or similar. We propose techniques that build on existing domain adaptation methods by explicitly modeling these relationships, and demonstrate empirically that they improve recognition accuracy in two scenarios, multicategory image classification and object detection in video.

Related Material

author = {Donahue, Jeff and Hoffman, Judy and Rodner, Erik and Saenko, Kate and Darrell, Trevor},
title = {Semi-supervised Domain Adaptation with Instance Constraints},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}