面向大规模图像分类的随机boosting
Stochastic Boosting for Large-scale Image Classification
目前,Boosting算法在图像处理和计算机视觉中已经得到广泛应用。许多工作涉及到boosting算法的设计和使用,但对于boosting算法在大规模数据上的训练却很少涉及。为了能让boosting处理大规模问题,我们利用随机梯度下降优化方法,提出了随机boosting（StocBoost）算法。为了能理解随机boosting的性能,随机boosting的收敛性在理论上进行了分析。实验结果表明随机boosting的训练速度比批处理方式更加快,在性能上接近甚至超过目前最好的方法。
Boosting has been extensively used in image processing or computer vision. Many work focuses on the design or the usage of boosting, but training boosting on large-scale datasets has barely been discussed. To handle large-scale problem, we present stochastic boosting (StocBoost) that relies on stochastic gradient descent (SGD). To understand the efficacy of StocBoost, the convergence is theoretically analyzed. Experimental results show that StocBoost is more fastthan batch ones, and is also comparable with the state-of-the-arts.
王丹、庞俊彪、尹宝才、黄庆明
计算技术、计算机技术
随机梯度下降分类提升算法大规模问题
Stochastic gradient descentClassificationBoostingLarge scale problem
王丹,庞俊彪,尹宝才,黄庆明.面向大规模图像分类的随机boosting[EB/OL].(2013-05-02)[2025-08-18].http://www.paper.edu.cn/releasepaper/content/201305-34.点此复制
评论