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 2201.05781cs.CV
收藏

OneDConv:变换不变表示的广义卷积

OneDConv: Generalized Convolution For Transform-Invariant Representation

South China University of Technology(华南理工大学)

Tong Zhang, Haohan Weng, Ke Yi, C. L. Philip Chen

摘要:

卷积神经网络(CNN)在各种视觉任务中表现出了强大的功能。然而,缺乏变换不变性限制了它们在复杂的现实世界中的进一步应用。在这项工作中,我们提出了一种新的广义一维卷积算子(OneDConv),它以计算和参数有效的方式基于输入特征动态地变换卷积核。该算子能自然地提取变换不变特征。它提高了卷积的鲁棒性和通用性,而不牺牲普通图像的性能。所提出的OneDConv算子可以替代普通卷积,因此它可以被纳入当前流行的卷积架构中,并很容易进行端到端的训练。在几个流行的基准测试中,OneDConv在规范和失真图像中的性能都优于原始卷积运算和其他提出的模型。

英文摘要:

Convolutional Neural Networks (CNNs) have exhibited their great power in a variety of vision tasks. However, the lack of transform-invariant property limits their further applications in complicated real-world scenarios. In this work, we proposed a novel generalized one dimension convolutional operator (OneDConv), which dynamically transforms the convolution kernels based on the input features in a computationally and parametrically efficient manner. The proposed operator can extract the transform-invariant features naturally. It improves the robustness and generalization of convolution without sacrificing the performance on common images. The proposed OneDConv operator can substitute the vanilla convolution, thus it can be incorporated into current popular convolutional architectures and trained end-to-end readily. On several popular benchmarks, OneDConv outperforms the original convolution operation and other proposed models both in canonical and distorted images.

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。

↑