{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/wavelet-convolutions-for-large-receptive","title":"Wavelet Convolutions for Large Receptive Fields","arxiv_id":"2407.05848","date":"2024-07-08","proceeding":null,"authors":["Shahaf E. Finder","Roy Amoyal","Eran Treister","Oren Freifeld"],"abstract":"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 $k \\times k$ 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.","url_abs":"https://arxiv.org/abs/2407.05848v2","url_pdf":"https://arxiv.org/pdf/2407.05848v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"wavelet-convolutions-for-large-receptive","repo_url":"https://github.com/bgu-cs-vil/wtconv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"2d-semantic-segmentation","task_name":"2D Semantic Segmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convnext","method_name":"ConvNeXt"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.05848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05848"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bgu-cs-vil/wtconv","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":7},"by_repo_kind":{"official":{"samples":14,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"89aebc2a59c89f7c","entry":"compute_scaled_weight","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/cuda_haar/haar_cuda.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/cuda_haar/haar_cuda.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89aebc2a59c89f7c"}},{"code_sha256_prefix":"65aed3f0fdef124d","entry":"compute_scaled_weight","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/triton_haar/triton_haar.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/triton_haar/triton_haar.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65aed3f0fdef124d"}},{"code_sha256_prefix":"68b01718f52888a0","entry":"create_1d_wavelet_filter","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"wtconv/util/wavelet.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/wtconv/util/wavelet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68b01718f52888a0"}},{"code_sha256_prefix":"1685a5e7e0c05088","entry":"create_2d_wavelet_filter","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"wtconv/util/wavelet.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/wtconv/util/wavelet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1685a5e7e0c05088"}},{"code_sha256_prefix":"d944fed242e85a94","entry":"get_input_grad","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"erf.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/erf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d944fed242e85a94"}},{"code_sha256_prefix":"7795b07b71124f9f","entry":"get_rectangle","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"erf.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/erf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7795b07b71124f9f"}},{"code_sha256_prefix":"84b9e513e0e6515a","entry":"scaled_depthwise_conv","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/triton_haar/triton_depthwise.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/triton_haar/triton_depthwise.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"84b9e513e0e6515a"}},{"code_sha256_prefix":"1cbae5666182a259","entry":"fused_haar_conv_scale","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/cuda_haar/haar_cuda.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/cuda_haar/haar_cuda.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1cbae5666182a259"}},{"code_sha256_prefix":"b1afaa284fa5ea22","entry":"haar2d","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/metal_haar/haar_metal.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/metal_haar/haar_metal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1afaa284fa5ea22"}},{"code_sha256_prefix":"98b6fd13f94b25f9","entry":"haar2d_double","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/metal_haar/haar_metal.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/metal_haar/haar_metal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98b6fd13f94b25f9"}},{"code_sha256_prefix":"1b783f2d139defa2","entry":"ihaar2d","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/metal_haar/haar_metal.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/metal_haar/haar_metal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b783f2d139defa2"}},{"code_sha256_prefix":"88b1d8105f215aad","entry":"process","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"erf.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/erf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88b1d8105f215aad"}},{"code_sha256_prefix":"be3a2755891acf65","entry":"wavelet_1d_transform","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"wtconv/util/wavelet.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/wtconv/util/wavelet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be3a2755891acf65"}},{"code_sha256_prefix":"03af63e169a4cb46","entry":"wavelet_branch","repo":"bgu-cs-vil/wtconv","repo_kind":"official","path":"fast_wtconv/cuda_haar/haar_cuda.py","file_url":"https://github.com/bgu-cs-vil/wtconv/blob/HEAD/fast_wtconv/cuda_haar/haar_cuda.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03af63e169a4cb46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}