Papers › Wavelet Convolutions for Large Receptive Fields

Wavelet Convolutions for Large Receptive Fields

8 Jul 2024arXiv:2407.05848archive 2025-07-28

Shahaf E. Finder, Roy Amoyal, Eran Treister, Oren Freifeld

In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper bound and saturated way before achieving a global receptive field. In this work, we demonstrate that by leveraging the Wavelet Transform (WT), it is, in fact, possible to obtain very large receptive fields without suffering from over-parameterization, e.g., for a k ×k receptive field, the number of trainable parameters in the proposed method grows only logarithmically with k. The proposed layer, named WTConv, can be used as a drop-in replacement in existing architectures, results in an effective multi-frequency response, and scales gracefully with the size of the receptive field. We demonstrate the effectiveness of the WTConv layer within ConvNeXt and MobileNetV2 architectures for image classification, as well as backbones for downstream tasks, and show it yields additional properties such as robustness to image corruption and an increased response to shapes over textures. Our code is available at https://github.com/BGU-CS-VIL/WTConv.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.05848")

Code

Syntology Ran 7 of 14 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bgu-cs-vil/wtconv officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 7 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
7unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from bgu-cs-vil/wtconv. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_scaled_weight bgu-cs-vil/wtconv/fast_wtconv/cuda_haar/haar_cuda.py official repository ran MIT (permissive) · 89aebc2a59c89f7c · report
compute_scaled_weight bgu-cs-vil/wtconv/fast_wtconv/triton_haar/triton_haar.py official repository ran MIT (permissive) · 65aed3f0fdef124d · report
create_1d_wavelet_filter bgu-cs-vil/wtconv/wtconv/util/wavelet.py official repository ran MIT (permissive) · 68b01718f52888a0 · report
create_2d_wavelet_filter bgu-cs-vil/wtconv/wtconv/util/wavelet.py official repository ran MIT (permissive) · 1685a5e7e0c05088 · report
get_input_grad bgu-cs-vil/wtconv/erf.py official repository ran MIT (permissive) · d944fed242e85a94 · report
get_rectangle bgu-cs-vil/wtconv/erf.py official repository ran MIT (permissive) · 7795b07b71124f9f · report
scaled_depthwise_conv bgu-cs-vil/wtconv/fast_wtconv/triton_haar/triton_depthwise.py official repository ran MIT (permissive) · 84b9e513e0e6515a · report
fused_haar_conv_scale bgu-cs-vil/wtconv/fast_wtconv/cuda_haar/haar_cuda.py official repository unverified MIT (permissive) · 1cbae5666182a259 · report
haar2d bgu-cs-vil/wtconv/fast_wtconv/metal_haar/haar_metal.py official repository unverified MIT (permissive) · b1afaa284fa5ea22 · report
haar2d_double bgu-cs-vil/wtconv/fast_wtconv/metal_haar/haar_metal.py official repository unverified MIT (permissive) · 98b6fd13f94b25f9 · report
ihaar2d bgu-cs-vil/wtconv/fast_wtconv/metal_haar/haar_metal.py official repository unverified MIT (permissive) · 1b783f2d139defa2 · report
process bgu-cs-vil/wtconv/erf.py official repository unverified MIT (permissive) · 88b1d8105f215aad · report
wavelet_1d_transform bgu-cs-vil/wtconv/wtconv/util/wavelet.py official repository unverified MIT (permissive) · be3a2755891acf65 · report
wavelet_branch bgu-cs-vil/wtconv/fast_wtconv/cuda_haar/haar_cuda.py official repository unverified MIT (permissive) · 03af63e169a4cb46 · report

Tasks

2D Object Detection2D Semantic SegmentationImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvNeXtConvolutionDepthwise ConvolutionDepthwise Separable ConvolutionInverted Residual BlockPointwise Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections