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 1301.3755cs.CV
收藏

基于梯度驱动学习的视觉流水特征提取模型池化

Gradient Driven Learning for Pooling in Visual Pipeline Feature Extraction Models

University of Tennessee(田纳西大学)

Derek Rose, Itamar Arel

摘要:

超参数选择仍然是一个艰巨的任务时,建立一个模式识别架构,表现良好,特别是在最近构建的视觉管道模型的特征提取。我们将现有管道中的池化重新制定为可调池化映射权重参数的函数,并建议使用来自梯度下降的监督误差信号来调整模型内的已建立映射。这种技术使我们能够了解模型中的设计选择,并专门化映射以聚合所呈现任务的不变性区域。初步结果显示,中等的潜在收益的分类精度和突出领域的重要性,在中间特征表示空间。

英文摘要:

Hyper-parameter selection remains a daunting task when building a pattern recognition architecture which performs well, particularly in recently constructed visual pipeline models for feature extraction. We re-formulate pooling in an existing pipeline as a function of adjustable pooling map weight parameters and propose the use of supervised error signals from gradient descent to tune the established maps within the model. This technique allows us to learn what would otherwise be a design choice within the model and specialize the maps to aggregate areas of invariance for the task presented. Preliminary results show moderate potential gains in classification accuracy and highlight areas of importance within the intermediate feature representation space.

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。

↑