{"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/transcending-the-limit-of-local-window","title":"Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary","arxiv_id":"2401.08209","date":"2024-01-16","proceeding":"CVPR 2024 1","authors":["Leheng Zhang","Yawei Li","Xingyu Zhou","Xiaorui Zhao","Shuhang Gu"],"abstract":"Single Image Super-Resolution is a classic computer vision problem that involves estimating high-resolution (HR) images from low-resolution (LR) ones. Although deep neural networks (DNNs), especially Transformers for super-resolution, have seen significant advancements in recent years, challenges still remain, particularly in limited receptive field caused by window-based self-attention. To address these issues, we introduce a group of auxiliary Adaptive Token Dictionary to SR Transformer and establish an ATD-SR method. The introduced token dictionary could learn prior information from training data and adapt the learned prior to specific testing image through an adaptive refinement step. The refinement strategy could not only provide global information to all input tokens but also group image tokens into categories. Based on category partitions, we further propose a category-based self-attention mechanism designed to leverage distant but similar tokens for enhancing input features. The experimental results show that our method achieves the best performance on various single image super-resolution benchmarks.","url_abs":"https://arxiv.org/abs/2401.08209v2","url_pdf":"https://arxiv.org/pdf/2401.08209v2.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":"transcending-the-limit-of-local-window","repo_url":"https://github.com/labshuhanggu/adaptive-token-dictionary","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"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":"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":[{"leaderboard":"/sota/image-super-resolution-on-set14","task":"Image Super-Resolution","dataset":"Set14","model":"ATD","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"29.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"ATD","rank_in_archive_order":16,"of":104,"metrics":{"PSNR":"29.24","SSIM":"0.7974"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.08209","atlas_url":"https://app.syntology.ai/?focus=2401.08209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08209"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/labshuhanggu/adaptive-token-dictionary","reach":null}],"summary":{"ran":9,"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":15,"ran":11,"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":"2d93e34cbbe0fa7b","entry":"AC_MSA","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d93e34cbbe0fa7b"}},{"code_sha256_prefix":"a705dbc0a3d310ee","entry":"ATD_CA","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a705dbc0a3d310ee"}},{"code_sha256_prefix":"ffc960c5105253ab","entry":"ConvFFN_td","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffc960c5105253ab"}},{"code_sha256_prefix":"6317975e251ab4b3","entry":"PatchEmbed","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6317975e251ab4b3"}},{"code_sha256_prefix":"3732cc4a6f0ef56f","entry":"PatchUnEmbed","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3732cc4a6f0ef56f"}},{"code_sha256_prefix":"a3aba55c35e501fd","entry":"Upsample","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3aba55c35e501fd"}},{"code_sha256_prefix":"9f0f80f58d07551b","entry":"UpsampleOneStep","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f0f80f58d07551b"}},{"code_sha256_prefix":"f6d717e16606d5e6","entry":"WindowAttention","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6d717e16606d5e6"}},{"code_sha256_prefix":"8962dc49cd030b9e","entry":"dwconv","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8962dc49cd030b9e"}},{"code_sha256_prefix":"71f42c96ab0f7f91","entry":"feature_shuffle","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71f42c96ab0f7f91"}},{"code_sha256_prefix":"631a9cdc62e42ba1","entry":"index_reverse","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"631a9cdc62e42ba1"}},{"code_sha256_prefix":"ea638ff98268e1f2","entry":"ATD","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea638ff98268e1f2"}},{"code_sha256_prefix":"7d7aefff486dc4f7","entry":"ATDB","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d7aefff486dc4f7"}},{"code_sha256_prefix":"3284755d16ba68ae","entry":"ATDTransformerLayer","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3284755d16ba68ae"}},{"code_sha256_prefix":"40f551c6bc695162","entry":"BasicBlock","repo":"labshuhanggu/adaptive-token-dictionary","repo_kind":"official","path":"basicsr/archs/atd_arch.py","file_url":"https://github.com/labshuhanggu/adaptive-token-dictionary/blob/HEAD/basicsr/archs/atd_arch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40f551c6bc695162"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}