arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.06408cs.CV
收藏

提高目标识别率的多层次上下文表示

Multilevel Context Representation for Improving Object Recognition

MindGarage(思维车库);University of Kaiserslautern(凯撒斯劳滕大学);Insiders Technologies GmbH(内部人科技有限公司);University of Fribourg(弗里堡大学)

Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki

摘要:

在这项工作中,我们提出了结合使用低和高级别块的卷积神经网络(CNN),以提高对象识别。虽然最近的研究集中在从所有层传播上下文,例如ResNet(包括非常低级别的层)或具有多个丢失层(例如GoogLeNet),但靠近高层的特征的重要性被忽略了。本文假设使用更接近高层的上下文提供了尺度和平移不变性,并且比仅使用顶层效果更好。特别是,我们通过在顶部$n$层中添加连接来扩展AlexNet和GoogLeNet。为了证明所提出的方法的有效性,我们在标准ImageNet任务上对其进行了评估。在不影响计算成本的情况下,分类误差的相对减少约为1-2%。此外,我们表明,这种方法是正交的典型的测试数据增强技术,最近推出的Szegedy等人。(导致运行时间减少144在测试时间)。

英文摘要:

In this work, we propose the combined usage of low- and high-level blocks of convolutional neural networks (CNNs) for improving object recognition. While recent research focused on either propagating the context from all layers, e.g. ResNet, (including the very low-level layers) or having multiple loss layers (e.g. GoogLeNet), the importance of the features close to the higher layers is ignored. This paper postulates that the use of context closer to the high-level layers provides the scale and translation invariance and works better than using the top layer only. In particular, we extend AlexNet and GoogLeNet by additional connections in the top $n$ layers. In order to demonstrate the effectiveness of the proposed approach, we evaluated it on the standard ImageNet task. The relative reduction of the classification error is around 1-2% without affecting the computational cost. Furthermore, we show that this approach is orthogonal to typical test data augmentation techniques, as recently introduced by Szegedy et al. (leading to a runtime reduction of 144 during test time).

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。

↑