可学习间距的膨胀卷积：超越双线性插值
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
AI总结：
本文提出用高斯插值等长程插值替代DCLS中的双线性插值，在不增加参数的情况下提升ConvNeXt和ConvFormer在ImageNet1k上的分类性能。
摘要：
可学习间距的膨胀卷积（DCLS）是最近提出的一种膨胀卷积变体，其中卷积核中非零元素之间的间距，或等价地它们的位置，是可学习的。非整数位置通过插值处理。得益于这一技巧，位置具有定义良好的梯度。原始的DCLS使用双线性插值，因此只考虑四个最近的像素。然而，我们在此表明，更长范围的插值，特别是高斯插值，能够在两个最先进的卷积架构（ConvNeXt和ConvFormer）上提高ImageNet1k分类的性能，而不会增加参数数量。该方法的代码基于PyTorch，可在https://github.com/K-H-Ismail/Dilated-Convolution-with-Learnable-Spacings-PyTorch获取。
英文摘要：
Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or equivalently their positions, are learnable. Non-integer positions are handled via interpolation. Thanks to this trick, positions have well-defined gradients. The original DCLS used bilinear interpolation, and thus only considered the four nearest pixels. Yet here we show that longer range interpolations, and in particular a Gaussian interpolation, allow improving performance on ImageNet1k classification on two state-of-the-art convolutional architectures (ConvNeXt and Conv\-Former), without increasing the number of parameters. The method code is based on PyTorch and is available at https://github.com/K-H-Ismail/Dilated-Convolution-with-Learnable-Spacings-PyTorch
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。
