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

摘要：pi最近开发了一种基于判别训练的可变形部分模型，用于检测图像中的物体。该模型在平均精度上比2006年PASCAL人物检测挑战中的最佳性能提高了两倍。在2007年的目标检测挑战赛中，我们的参赛作品赢得了六个组别的冠军。自2007年挑战赛以来的改进改进了我们的结果，因此我们现在在20个类别中有10个类别（包括个人类别）的表现超过了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，我们称之为潜在支持向量机（LSVM）。我们建议以多种方式扩展这种方法。研究将侧重于更深层的潜在信息，如子分类（混合模型）、三维姿态和图像/地面分割。他们还将使用类层次结构、可视单词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，这些模型参数是高度非线性的。本研究的所有方面都与实证表现密切相关——除非能真正提高技术水平，否则不会采用任何方法。我们的目标一直是，并将继续是，通过使用语义更深的模型和改进的通用机器学习方法来提高技术水平。这个项目的进展可以在http://tic.uchicago.edu/ ~dmcallester/objects.html上找到

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