{"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/decouple-learning-for-parameterized-image","title":"Decouple Learning for Parameterized Image Operators","arxiv_id":"1807.08186","date":"2018-07-21","proceeding":"ECCV 2018 9","authors":["Qingnan Fan","Dong-Dong Chen","Lu Yuan","Gang Hua","Nenghai Yu","Baoquan Chen"],"abstract":"Many different deep networks have been used to approximate, accelerate or\nimprove traditional image operators, such as image smoothing, super-resolution\nand denoising. Among these traditional operators, many contain parameters which\nneed to be tweaked to obtain the satisfactory results, which we refer to as\n\"parameterized image operators\". However, most existing deep networks trained\nfor these operators are only designed for one specific parameter configuration,\nwhich does not meet the needs of real scenarios that usually require flexible\nparameters settings. To overcome this limitation, we propose a new decouple\nlearning algorithm to learn from the operator parameters to dynamically adjust\nthe weights of a deep network for image operators, denoted as the base network.\nThe learned algorithm is formed as another network, namely the weight learning\nnetwork, which can be end-to-end jointly trained with the base network.\nExperiments demonstrate that the proposed framework can be successfully applied\nto many traditional parameterized image operators. We provide more analysis to\nbetter understand the proposed framework, which may inspire more promising\nresearch in this direction. Our codes and models have been released in\nhttps://github.com/fqnchina/DecoupleLearning","url_abs":"http://arxiv.org/abs/1807.08186v2","url_pdf":"http://arxiv.org/pdf/1807.08186v2.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":"decouple-learning-for-parameterized-image","repo_url":"https://github.com/fqnchina/DecoupleLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"image-smoothing","task_name":"image smoothing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.08186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.08186"}},"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/fqnchina/DecoupleLearning","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"e4474e5f6c205b77","entry":"var_custom_collate","repo":"fqnchina/DecoupleLearning","repo_kind":"official","path":"train_10_operator_model.py","file_url":"https://github.com/fqnchina/DecoupleLearning/blob/HEAD/train_10_operator_model.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":"e4474e5f6c205b77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}