{"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/efficient-transformer-for-single-image-super","title":"Transformer for Single Image Super-Resolution","arxiv_id":"2108.11084","date":"2021-08-25","proceeding":null,"authors":["Zhisheng Lu","Juncheng Li","Hong Liu","Chaoyan Huang","Linlin Zhang","Tieyong Zeng"],"abstract":"Single image super-resolution (SISR) has witnessed great strides with the development of deep learning. However, most existing studies focus on building more complex networks with a massive number of layers. Recently, more and more researchers start to explore the application of Transformer in computer vision tasks. However, the heavy computational cost and high GPU memory occupation of the vision Transformer cannot be ignored. In this paper, we propose a novel Efficient Super-Resolution Transformer (ESRT) for SISR. ESRT is a hybrid model, which consists of a Lightweight CNN Backbone (LCB) and a Lightweight Transformer Backbone (LTB). Among them, LCB can dynamically adjust the size of the feature map to extract deep features with a low computational cost. LTB is composed of a series of Efficient Transformers (ET), which occupies a small GPU memory occupation, thanks to the specially designed Efficient Multi-Head Attention (EMHA). Extensive experiments show that ESRT achieves competitive results with low computational costs. Compared with the original Transformer which occupies 16,057M GPU memory, ESRT only occupies 4,191M GPU memory. All codes are available at https://github.com/luissen/ESRT.","url_abs":"https://arxiv.org/abs/2108.11084v3","url_pdf":"https://arxiv.org/pdf/2108.11084v3.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":"efficient-transformer-for-single-image-super","repo_url":"https://github.com/luissen/esrt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"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"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.11084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11084"}},"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/luissen/esrt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"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":"3ac6b7d76e8e3584","entry":"drop_path","repo":"luissen/esrt","repo_kind":"official","path":"util/transformer.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/util/transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"code_sha256_prefix":"b6a238bb90c0069b","entry":"norm","repo":"luissen/esrt","repo_kind":"official","path":"model/block.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/model/block.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6a238bb90c0069b"}},{"code_sha256_prefix":"4a56ce1917d87f9b","entry":"pad","repo":"luissen/esrt","repo_kind":"official","path":"model/block.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/model/block.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a56ce1917d87f9b"}},{"code_sha256_prefix":"14982a5b13861f94","entry":"time_text","repo":"luissen/esrt","repo_kind":"official","path":"utils.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14982a5b13861f94"}},{"code_sha256_prefix":"61eaa43ff60ccf54","entry":"build_position_encoding","repo":"luissen/esrt","repo_kind":"official","path":"util/position.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/util/position.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":"61eaa43ff60ccf54"}},{"code_sha256_prefix":"377d0526c105eca0","entry":"conv_layer","repo":"luissen/esrt","repo_kind":"official","path":"model/block.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/model/block.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":"377d0526c105eca0"}},{"code_sha256_prefix":"6a89bdb621ad4a99","entry":"default_conv","repo":"luissen/esrt","repo_kind":"official","path":"model/common.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/model/common.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":"6a89bdb621ad4a99"}},{"code_sha256_prefix":"464350a5383e9f3f","entry":"extract_image_patches","repo":"luissen/esrt","repo_kind":"official","path":"util/tools.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/util/tools.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":"464350a5383e9f3f"}},{"code_sha256_prefix":"cffc08be0b9c7f7f","entry":"normalize","repo":"luissen/esrt","repo_kind":"official","path":"util/tools.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/util/tools.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":"cffc08be0b9c7f7f"}},{"code_sha256_prefix":"fd1ff803fc207b8e","entry":"same_padding","repo":"luissen/esrt","repo_kind":"official","path":"util/tools.py","file_url":"https://github.com/luissen/esrt/blob/HEAD/util/tools.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":"fd1ff803fc207b8e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}