{"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/spiking-wavelet-transformer","title":"Spiking Wavelet Transformer","arxiv_id":"2403.11138","date":"2024-03-17","proceeding":null,"authors":["Yuetong Fang","Ziqing Wang","Lingfeng Zhang","Jiahang Cao","Honglei Chen","Renjing Xu"],"abstract":"Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep learning by emulating the event-driven processing manner of the brain. Incorporating Transformers with SNNs has shown promise for accuracy. However, they struggle to learn high-frequency patterns, such as moving edges and pixel-level brightness changes, because they rely on the global self-attention mechanism. Learning these high-frequency representations is challenging but essential for SNN-based event-driven vision. To address this issue, we propose the Spiking Wavelet Transformer (SWformer), an attention-free architecture that effectively learns comprehensive spatial-frequency features in a spike-driven manner by leveraging the sparse wavelet transform. The critical component is a Frequency-Aware Token Mixer (FATM) with three branches: 1) spiking wavelet learner for spatial-frequency domain learning, 2) convolution-based learner for spatial feature extraction, and 3) spiking pointwise convolution for cross-channel information aggregation - with negative spike dynamics incorporated in 1) to enhance frequency representation. The FATM enables the SWformer to outperform vanilla Spiking Transformers in capturing high-frequency visual components, as evidenced by our empirical results. Experiments on both static and neuromorphic datasets demonstrate SWformer's effectiveness in capturing spatial-frequency patterns in a multiplication-free and event-driven fashion, outperforming state-of-the-art SNNs. SWformer achieves a 22.03% reduction in parameter count, and a 2.52% performance improvement on the ImageNet dataset compared to vanilla Spiking Transformers. The code is available at: https://github.com/bic-L/Spiking-Wavelet-Transformer.","url_abs":"https://arxiv.org/abs/2403.11138v5","url_pdf":"https://arxiv.org/pdf/2403.11138v5.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":"spiking-wavelet-transformer","repo_url":"https://github.com/bic-l/spiking-wavelet-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"snn","method_name":"SNN"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.11138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11138"}},"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/bic-l/spiking-wavelet-transformer","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"8eee4204b6767c33","entry":"fast_collate","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/loader.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8eee4204b6767c33"}},{"code_sha256_prefix":"152a26aee4531e51","entry":"haar_1d_matrix","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/wavelet_layers.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/wavelet_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"152a26aee4531e51"}},{"code_sha256_prefix":"5f5efd9540c93d2b","entry":"haar_matrix","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/wavelet_layers.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/wavelet_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f5efd9540c93d2b"}},{"code_sha256_prefix":"f3b8ac54d0aac694","entry":"normalize_haar_matrix","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/wavelet_layers.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/wavelet_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3b8ac54d0aac694"}},{"code_sha256_prefix":"2d7b973a4b160d73","entry":"shear_y","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/aa_snn.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/aa_snn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d7b973a4b160d73"}},{"code_sha256_prefix":"d5a693c429aa8571","entry":"transforms_imagenet_eval","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/transforms_factory.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/transforms_factory.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5a693c429aa8571"}},{"code_sha256_prefix":"c82a60e3c9859e18","entry":"transforms_noaug_train","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/transforms_factory.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/transforms_factory.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c82a60e3c9859e18"}},{"code_sha256_prefix":"b31e84df5541213a","entry":"shear_x","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/aa_snn.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/aa_snn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b31e84df5541213a"}},{"code_sha256_prefix":"61f2a3e08a11e1f5","entry":"translate_x_rel","repo":"bic-l/spiking-wavelet-transformer","repo_kind":"official","path":"cifar10-100/aa_snn.py","file_url":"https://github.com/bic-l/spiking-wavelet-transformer/blob/HEAD/cifar10-100/aa_snn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61f2a3e08a11e1f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}