arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.09643cs.CVcs.LGeess.IV
收藏

CPWC:用于对象识别的上下文逐点卷积

CPWC: Contextual Point Wise Convolution for Object Recognition

IIT Kanpur(印度理工学院坎普尔分校)

Pratik Mazumder, Pravendra Singh, Vinay Namboodiri

摘要:

卷积层是深度学习成功背后的主要驱动力。逐点卷积(PWC)是一种1x1卷积滤波器,主要用于参数减少。然而,PWC忽略了它正在处理的点周围的空间信息。该设计是选择性的,以便减少总体参数和计算。然而,我们假设PWC的这个缺点对网络性能有重大影响。我们提出了一种逐点卷积的替代设计,它有效地利用了输入的空间信息。我们的设计显着提高了网络的性能,而不会大幅增加参数和计算的数量。我们的实验表明,我们的设计结果在分类以及检测网络的性能显着改善。

英文摘要:

Convolutional layers are a major driving force behind the successes of deep learning. Pointwise convolution (PWC) is a 1x1 convolutional filter that is primarily used for parameter reduction. However, the PWC ignores the spatial information around the points it is processing. This design is by choice, in order to reduce the overall parameters and computations. However, we hypothesize that this shortcoming of PWC has a significant impact on the network performance. We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently. Our design significantly improves the performance of the networks without substantially increasing the number of parameters and computations. We experimentally show that our design results in significant improvement in the performance of the network for classification as well as detection.

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。

↑