{"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/adaptive-cross-layer-attention-for-image-1","title":"Adaptive Cross-Layer Attention for Image Restoration","arxiv_id":"2203.03619","date":"2022-03-04","proceeding":null,"authors":["Yancheng Wang","Ning Xu","Yingzhen Yang"],"abstract":"Non-local attention module has been proven to be crucial for image restoration. Conventional non-local attention processes features of each layer separately, so it risks missing correlation between features among different layers. To address this problem, we aim to design attention modules that aggregate information from different layers. Instead of finding correlated key pixels within the same layer, each query pixel is encouraged to attend to key pixels at multiple previous layers of the network. In order to efficiently embed such attention design into neural network backbones, we propose a novel Adaptive Cross-Layer Attention (ACLA) module. Two adaptive designs are proposed for ACLA: (1) adaptively selecting the keys for non-local attention at each layer; (2) automatically searching for the insertion locations for ACLA modules. By these two adaptive designs, ACLA dynamically selects a flexible number of keys to be aggregated for non-local attention at previous layer while maintaining a compact neural network with compelling performance. Extensive experiments on image restoration tasks, including single image super-resolution, image denoising, image demosaicing, and image compression artifacts reduction, validate the effectiveness and efficiency of ACLA. The code of ACLA is available at \\url{https://github.com/SDL-ASU/ACLA}.","url_abs":"https://arxiv.org/abs/2203.03619v3","url_pdf":"https://arxiv.org/pdf/2203.03619v3.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":"adaptive-cross-layer-attention-for-image-1","repo_url":"https://github.com/sdl-asu/acla","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.03619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03619"}},"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/sdl-asu/acla","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"8b0e794d4d8f9b13","entry":"default_conv","repo":"sdl-asu/acla","repo_kind":"official","path":"SR/model/common.py","file_url":"https://github.com/sdl-asu/acla/blob/HEAD/SR/model/common.py","link_basis":"harvester_set","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":"8b0e794d4d8f9b13"}},{"code_sha256_prefix":"b2fb8159f199e5b8","entry":"get_parameter_number","repo":"sdl-asu/acla","repo_kind":"official","path":"SR/model/common.py","file_url":"https://github.com/sdl-asu/acla/blob/HEAD/SR/model/common.py","link_basis":"harvester_set","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":"b2fb8159f199e5b8"}},{"code_sha256_prefix":"74343d6a0353947e","entry":"deform_conv2d","repo":"sdl-asu/acla","repo_kind":"official","path":"SR/model/ACL_Attention.py","file_url":"https://github.com/sdl-asu/acla/blob/HEAD/SR/model/ACL_Attention.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":"74343d6a0353947e"}},{"code_sha256_prefix":"5ecf1cc45bcc3af5","entry":"make_model","repo":"sdl-asu/acla","repo_kind":"official","path":"SR/model/carn.py","file_url":"https://github.com/sdl-asu/acla/blob/HEAD/SR/model/carn.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":"5ecf1cc45bcc3af5"}},{"code_sha256_prefix":"415fea29e966e23f","entry":"make_same_layer_superimposed","repo":"sdl-asu/acla","repo_kind":"official","path":"SR/model/common.py","file_url":"https://github.com/sdl-asu/acla/blob/HEAD/SR/model/common.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":"415fea29e966e23f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}