Unsupervised sub-categorization for object detection: Finding cars from a driving vehicle

We present a novel algorithm for unsupervised subcategorization of an object class, in the context of object detection. Dividing the detection problem into smaller subproblems simplifies the object vs. background classification. The algorithm uses an iterative split-and-merge procedure and uses both object and non-object information. Sub-classes are automatically split into two new classes if the visual variation is too large, while two classes are merged if they are visually similar. After each iteration, samples are relabeled to the most preferred subclasses. In contrast to existing literature on unsupervised sub- categorization, our approach does not fix the number of final subclasses and determines this number using a visual similarity measure. Because we use a fast stochastic learning algorithm, full retraining and relabeling can be applied at each iteration. We show that the algorithm significantly outperforms state-of-the-art multi-class algorithms for a car detection problem using standard HOG features and simple linear classification, while significantly decreasing training time to a few minutes. Additionally, for our car detection problem, the identified subclasses by the algorithm were semantically meaningful and reveal the viewpoint of the object without the use of any motion information.