arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1404.0334cs.CVcs.LG
收藏

主动可变形零件模型

Active Deformable Part Models

University of Pennsylvania(宾夕法尼亚大学)

Menglong Zhu, Nikolay Atanasov, George J. Pappas, Kostas Daniilidis

摘要:

本文提出了一种基于部分的目标检测的主动方法,该方法优化了部分滤波器评估的顺序以及停止和进行预测的时间。描述零件响应的统计数据从训练数据中学习,并用于将零件调度问题形式化为离线优化。应用动态规划来获得一个策略,该策略平衡了零件评估的数量与分类精度。在推理过程中,该策略被用作一个查找表,根据观察到的滤波器响应来选择部分阶数和停止时间。在PASCAL VOC 2007和2010数据集上进行评估时,该方法比使用可变形零件模型(未优化零件顺序)的级联检测更快,精度损失可忽略不计。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑