A fundamental problem in image analysis is the integration of information across scale to detect and classify objects. We have developed, within a machine learning framework, two classes of multi-resolution models for integrating scale information for object detection and classification- -a discriminative model called the hierarchical pyramid neural network (HPNN) and a generative model called a hierarchical image probability (HIP) model. Using receiver operating characteristic (ROC) analysis, we show that these models can significantly reduce the false positive rates for a well-established computer-aided diagnosis (CAD) system.