Computer Vision and Image Understanding
Image and Vision Computing
Undoing the damage of dataset bias
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Alternative search techniques for face detection using location estimation and binary features
Computer Vision and Image Understanding
Visual interestingness in image sequences
Proceedings of the 21st ACM international conference on Multimedia
Undo the codebook bias by linear transformation for visual applications
Proceedings of the 21st ACM international conference on Multimedia
Scene transformation for detector adaptation
Pattern Recognition Letters
| Hi-index | 0.00 |
Many classifiers are trained with massive training sets only to be applied at test time on data from a different distribution. How can we rapidly and simply adapt a classifier to a new test distribution, even when we do not have access to the original training data? We present an on-line approach for rapidly adapting a "black box" classifier to a new test data set without retraining the classifier or examining the original optimization criterion. Assuming the original classifier outputs a continuous number for which a threshold gives the class, we reclassify points near the original boundary using a Gaussian process regression scheme. We show how this general procedure can be used in the context of a classifier cascade, demonstrating performance that far exceeds state-of-the-art results in face detection on a standard data set. We also draw connections to work in semi-supervised learning, domain adaptation, and information regularization.