mlsanityData to 14 Oct 2026

Dilated Convolution with Learnable Spacings: beyond bilinear interpolation

arXiv 2306.00817 ↗First posted 1 Jun 2023cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 20 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

16 of 20 references.

References · 16

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2022A ConvNet for the 2020scited by 3,579
  3. 2017Deformable Convolutional Networkscited by 1,488
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  5. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  6. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  7. 2022MetaFormer Baselines for Visioncited by 132
  8. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 120
  9. 2021FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizescited by 66
  10. 2016Structured Receptive Fields in CNNscited by 32
  11. 2021Resolution learning in deep convolutional networks using scale-space theorycited by 26
  12. 2021Dilated convolution with learnable spacingscited by 20
4 more
  1. 2019Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fieldscited by 11
  2. 2023SMPConv: Self-moving Point Representations for Continuous Convolutioncited by 6
  3. 2023Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fieldscited by 5
  4. 2022Gaussian Mixture Convolution Networkscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2023Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacingscited by 50
  2. 2023Audio classification with Dilated Convolution with Learnable Spacingscited by 1
  3. 2024Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM studycited by 0
  4. 2025mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modelingcited by 0