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

翻译后摘要：PI最近开发了一个歧视性训练的可变形部分为基础的模型，用于检测图像中的对象。该模型在2006年PASCAL人物检测挑战中的最佳性能上实现了平均精度的两倍提高。我们在2007年物体探测挑战赛中赢得了六个班级的冠军。自2007年挑战赛以来的修改改善了我们的结果，使我们现在在20个类别中的10个类别（包括个人类别）中超越了2007年挑战赛的最佳结果。 这些成就依赖于一种新开发的潜变量模型的判别训练方法，我们称之为潜SVM（LSVM）。 我们建议以各种方式扩展这种方法。研究将集中在更深层次的潜在信息，如子分类（混合模型），三维姿态，和图形/地面分割。他们还将使用类层次结构、可视字和具有部件和子部件的层次对象模型。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，这些模型在模型参数中是高度非线性的。这项研究的所有方面都与经验性能密切相关--除非它实际上改善了最先进的技术，否则不会采用任何方法。我们的目标一直是，并将继续是，通过使用语义上更深入的模型和改进的通用机器学习方法来改善最先进的技术。有关该项目的进展，请访问http：/ttic.uchicago.edu/ www.dmcallester/objects.html

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