Learning to Localize Objects with Structured Output Regression

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 traini...

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Matthew B. Blaschko, Christoph H. Lampert
• Keywords: Binary Classifier, Binary Training, Computer Vision, ECCV 2008, Localization Task, Object Localization, Structured Training Procedure