RI-Small: Collaborative Research: Discriminative Latent Variable Object Detection

RI-Small：协作研究：判别性潜变量目标检测

• 批准号: 0812428
• 负责人: Deva Ramanan
• 金额: --
• 依托单位: University of California-Irvine
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2008
• 资助国家: 美国
• 起止时间: 2008-09-15 至 2011-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0812428&HistoricalAwards=false
• 关键词: RI; Small; Collaborative; Research; Discriminative

Abstract:The PIs have recently developed a discriminatively trained deformable part based model for detecting objects in images. This model achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. Our entry in the 2007 object detection challenge won in six classes. Modifications since the 2007 challenge have improved our results so that we now outperform the best 2007 challenge results in ten of twenty classes including the person class. These accomplishments rely on a newly developed approach to discriminative training for latent variable models which we call a latent SVM (LSVM). We propose to extend this methodology in a variety of ways. The research will focus on deeper latent information such as subclassification (mixture models), three dimensional pose, and figure/ground segmentations. They will also use class hierarchies, visual words, and hierarchical object models with parts and sub-parts. We also propose a general methodology for using SVM training to train models, such as geometry-based 3D models, which are highly nonlinear in model parameters. All aspects of this research are strongly tied to empirical performance -- no method will be adopted unless it actually improves the state of the art. The goal has been, and will continue to be, to improve the state of the art through the use of semantically deeper models and improved general purpose machine learning methods.Progress on this project can be found at http:/ttic.uchicago.edu/ ~dmcallester/objects.html

摘要：PI 最近开发了一种基于判别训练的可变形部件模型，用于检测图像中的对象。该模型的平均精度比 2006 年 PASCAL 人物检测挑战赛中的最佳性能提高了两倍。我们在 2007 年对象检测挑战赛中赢得了六个类别的冠军。自 2007 年挑战赛以来的修改提高了我们的成绩，因此我们现在在 20 个类别中的 10 个类别（包括个人类别）中超越了 2007 年挑战赛的最佳成绩。 这些成就依赖于一种新开发的潜在变量模型判别训练方法，我们称之为潜在 SVM (LSVM)。 我们建议以多种方式扩展这种方法。该研究将重点关注更深层次的潜在信息，例如子分类（混合模型）、三维姿势和图形/地面分割。他们还将使用类层次结构、视觉词汇以及带有部件和子部件的分层对象模型。我们还提出了一种使用 SVM 训练来训练模型的通用方法，例如基于几何的 3D 模型，这些模型的模型参数是高度非线性的。这项研究的所有方面都与实证表现密切相关——除非确实提高了现有技术水平，否则不会采用任何方法。我们的目标一直是，并将继续是，通过使用语义更深层次的模型和改进的通用机器学习方法来提高现有技术水平。该项目的进展可以在 http://ttic.uchicago.edu/~dmcallester/objects.html 上找到。