Looking outside of the Box: Object Detection and Localization with Multi-scale Patterns

Eshed Ohn-Bar, M. M. Trivedi

Published 2015-05-14Version 1

Detection and localization of objects at multiple scales often involves sliding a single scale template in order to score windows at different scales independently. Nonetheless, multi-scale visual information at a given image location is highly correlated. This fundamental insight allows us to generalize the traditional multi-scale sliding window technique by jointly considering image features at all scales in order to detect and localize objects. Two max-margin approaches are studied for learning the multi-scale templates and leveraging the highly structured multi-scale information which would have been ignored if a single-scale template was used. The multi-scale formulation is shown to significantly improve general detection performance (measured on the PASCAL VOC dataset). The experimental analysis shows the method to be effective with different visual features, both HOG and CNN. Surprisingly, for a given window in a specific scale, visual information from windows at the same image location but other scales (`out-of-scale' information) contains most of the discriminative information for detection.