This paper presents a new face detection method. We train a model that predicts the Jaccard distance between a sample sub-window and the ground truth face location. This model produces continuous outputs as opposite to the binary output produced by the widely used boosted cascade classifiers. To train this model we introduce a generalization of the binary classification boosting algorithms in which arbitrary smooth loss functions can be optimized. This way single output regression and binary classification models can be trained with the same procedure. Our method presents several significant advantages. First, it circumvents the need for a specific discretization of the location and scale during testing. Second, it provides an approximation of the search direction (in location and scale) towards the nearest ground truth location. And finally, the training set consists of more diverse samples (e.g. samples covering portions of the faces) that cannot be used to train a classifier. We provide experimental results on BioID face dataset to compare our method with the sliding-windows approach.