Dilated Convolution with Learnable Spacings: beyond bilinear interpolation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Dilated Convolution with Learnable Spacings: beyond bilinear interpolation

Résumé

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 ConvFormer), without increasing the number of parameters. The method code is based on PyTorch and is available at github.com/K-H-Ismail/Dilated-Convolutionwith-Learnable-Spacings-PyTorch.
Fichier principal
Vignette du fichier
dcls_icml_workshop.pdf (367.49 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04313620 , version 1 (29-11-2023)

Identifiants

  • HAL Id : hal-04313620 , version 1

Citer

Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier. Dilated Convolution with Learnable Spacings: beyond bilinear interpolation. Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators (ICML 2023), Jul 2023, Honolulu, United States. pp.1--7. ⟨hal-04313620⟩
47 Consultations
28 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More