arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.04232cs.CVcs.LG
收藏

DCNN节食:减少训练集大小的采样策略

DCNNs on a Diet: Sampling Strategies for Reducing the Training Set Size

Maya Kabkab, Azadeh Alavi, Rama Chellappa

摘要:

大规模监督分类算法,特别是基于深度卷积神经网络(DCNN)的算法,需要大量的训练数据来实现最先进的性能。减少这种数据要求将大大加快训练过程,并可能提高泛化能力。出于这一目标,我们考虑的任务,自适应地找到简洁的训练子集,将迭代地呈现给学习者。我们使用凸优化方法,基于一个客观的标准和反馈的分类器的当前性能,有效地识别信息样本训练on.We提出了一种算法,将优化问题分解为更小的每类问题,可以并行解决。我们在标准分类任务上测试了我们的方法,并证明了它在减少训练集大小而不影响性能方面的有效性。我们还表明,我们的方法可以使分类器更强大的标签噪声和类不平衡的存在。

英文摘要:

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would significantly speed up the training process and possibly improve generalization. Motivated by this objective, we consider the task of adaptively finding concise training subsets which will be iteratively presented to the learner. We use convex optimization methods, based on an objective criterion and feedback from the current performance of the classifier, to efficiently identify informative samples to train on. We propose an algorithm to decompose the optimization problem into smaller per-class problems, which can be solved in parallel. We test our approach on standard classification tasks and demonstrate its effectiveness in decreasing the training set size without compromising performance. We also show that our approach can make the classifier more robust in the presence of label noise and class imbalance.

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。

↑