Learning to localize objects with structured output regression

DMCA

Learning to localize objects with structured output regression (2008)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Matthew B. Blaschko , Christoph H. Lampert

Venue:	In ECCV
Citations:	125 - 15 self

BibTeX

@INPROCEEDINGS{Blaschko08learningto,
    author = {Matthew B. Blaschko and Christoph H. Lampert},
    title = {Learning to localize objects with structured output regression},
    booktitle = {In ECCV},
    year = {2008}
}

OpenURL

Abstract

Abstract. Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization task. First a binary classifier is trained using a sample of positive and negative examples, and this classifier is subsequently applied to multiple regions within test images. We propose instead to treat object localization in a principled way by posing it as a problem of predicting structured data: we model the problem not as binary classification, but as the prediction of the bounding box of objects located in images. The use of a joint-kernel framework allows us to formulate the training procedure as a generalization of an SVM, which can be solved efficiently. We further improve computational efficiency by using a branch-and-bound strategy for localization during both training and testing. Experimental evaluation on the PASCAL VOC and TU Darmstadt datasets show that the structured training procedure improves performance over binary training as well as the best previously published scores. 1

Keyphrases

structured output regression object localization binary classification computational efficiency binary training localization task joint-kernel framework test image principled way branch-and-bound strategy negative example multiple region pascal voc structured training procedure experimental evaluation binary classifier window classifier training procedure tu darmstadt

DMCA