Active Deformable Part Models
This work addresses efficiency in object detection for computer vision applications, but it is incremental as it builds on existing deformable part models.
The paper tackles the problem of speeding up part-based object detection by optimizing the order and stopping time of part filter evaluations, achieving faster detection than cascade methods with negligible accuracy loss on PASCAL VOC datasets.
This paper presents an active approach for part-based object detection, which optimizes the order of part filter evaluations and the time at which to stop and make a prediction. Statistics, describing the part responses, are learned from training data and are used to formalize the part scheduling problem as an offline optimization. Dynamic programming is applied to obtain a policy, which balances the number of part evaluations with the classification accuracy. During inference, the policy is used as a look-up table to choose the part order and the stopping time based on the observed filter responses. The method is faster than cascade detection with deformable part models (which does not optimize the part order) with negligible loss in accuracy when evaluated on the PASCAL VOC 2007 and 2010 datasets.