{"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/hybrid-spectral-denoising-transformer-with","title":"Hybrid Spectral Denoising Transformer with Guided Attention","arxiv_id":"2303.09040","date":"2023-03-16","proceeding":"ICCV 2023 1","authors":["Zeqiang Lai","Chenggang Yan","Ying Fu"],"abstract":"In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral image denoising. Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility. To address these issues, we introduce a hybrid approach that combines the advantages of both models with a Spatial-Spectral Separable Convolution (S3Conv), Guided Spectral Self-Attention (GSSA), and Self-Modulated Feed-Forward Network (SM-FFN). Our S3Conv works as a lightweight alternative to 3D convolution, which extracts more spatial-spectral correlated features while keeping the flexibility to tackle HSIs with an arbitrary number of bands. These features are then adaptively processed by GSSA which per-forms 3D self-attention across the spectral bands, guided by a set of learnable queries that encode the spectral signatures. This not only enriches our model with powerful capabilities for identifying global spectral correlations but also maintains linear complexity. Moreover, our SM-FFN proposes the self-modulation that intensifies the activations of more informative regions, which further strengthens the aggregated features. Extensive experiments are conducted on various datasets under both simulated and real-world noise, and it shows that our HSDT significantly outperforms the existing state-of-the-art methods while maintaining low computational overhead. Code is at https: //github.com/Zeqiang-Lai/HSDT.","url_abs":"https://arxiv.org/abs/2303.09040v2","url_pdf":"https://arxiv.org/pdf/2303.09040v2.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":"hybrid-spectral-denoising-transformer-with","repo_url":"https://github.com/zeqiang-lai/hsdt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"hyperspectral-image-denoising","task_name":"Hyperspectral Image Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"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=2303.09040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09040"}},"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":"deterministic:regex_extraction","url":"https://github.com/Zeqiang-Lai/HSDT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"80b8d6eefd57cc1c","entry":"DownConv","repo":"Zeqiang-Lai/HSDT","repo_kind":"official","path":"train/model/hsdt/qrnn/arch.py","file_url":"https://github.com/Zeqiang-Lai/HSDT/blob/HEAD/train/model/hsdt/qrnn/arch.py","link_basis":"harvester_set","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":"80b8d6eefd57cc1c"}},{"code_sha256_prefix":"c7d3569dc9404dff","entry":"PlainConv","repo":"Zeqiang-Lai/HSDT","repo_kind":"official","path":"train/model/hsdt/qrnn/arch.py","file_url":"https://github.com/Zeqiang-Lai/HSDT/blob/HEAD/train/model/hsdt/qrnn/arch.py","link_basis":"harvester_set","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":"c7d3569dc9404dff"}},{"code_sha256_prefix":"977e69ed58e173b8","entry":"UpConv","repo":"Zeqiang-Lai/HSDT","repo_kind":"official","path":"train/model/hsdt/qrnn/arch.py","file_url":"https://github.com/Zeqiang-Lai/HSDT/blob/HEAD/train/model/hsdt/qrnn/arch.py","link_basis":"harvester_set","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":"977e69ed58e173b8"}},{"code_sha256_prefix":"fff345b9f7828a6b","entry":"make_dataset","repo":"Zeqiang-Lai/HSDT","repo_kind":"official","path":"train/hsi_setup.py","file_url":"https://github.com/Zeqiang-Lai/HSDT/blob/HEAD/train/hsi_setup.py","link_basis":"harvester_set","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":"fff345b9f7828a6b"}},{"code_sha256_prefix":"81ceb1c537a2009a","entry":"repeat","repo":"Zeqiang-Lai/HSDT","repo_kind":"official","path":"hsdt/sepconv.py","file_url":"https://github.com/Zeqiang-Lai/HSDT/blob/HEAD/hsdt/sepconv.py","link_basis":"harvester_set","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":"81ceb1c537a2009a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}