{"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/towards-effective-multiple-in-one-image","title":"Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy","arxiv_id":"2401.03379","date":"2024-01-07","proceeding":null,"authors":["Xiangtao Kong","Chao Dong","Lei Zhang"],"abstract":"While single task image restoration (IR) has achieved significant successes, it remains a challenging issue to train a single model which can tackle multiple IR tasks. In this work, we investigate in-depth the multiple-in-one (MiO) IR problem, which comprises seven popular IR tasks. We point out that MiO IR faces two pivotal challenges: the optimization of diverse objectives and the adaptation to multiple tasks. To tackle these challenges, we present two simple yet effective strategies. The first strategy, referred to as sequential learning, attempts to address how to optimize the diverse objectives, which guides the network to incrementally learn individual IR tasks in a sequential manner rather than mixing them together. The second strategy, i.e., prompt learning, attempts to address how to adapt to the different IR tasks, which assists the network to understand the specific task and improves the generalization ability. By evaluating on 19 test sets, we demonstrate that the sequential and prompt learning strategies can significantly enhance the MiO performance of commonly used CNN and Transformer backbones. Our experiments also reveal that the two strategies can supplement each other to learn better degradation representations and enhance the model robustness. It is expected that our proposed MiO IR formulation and strategies could facilitate the research on how to train IR models with higher generalization capabilities.","url_abs":"https://arxiv.org/abs/2401.03379v3","url_pdf":"https://arxiv.org/pdf/2401.03379v3.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":"towards-effective-multiple-in-one-image","repo_url":"https://github.com/xiangtaokong/mioir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-effective-multiple-in-one-image","repo_url":"https://github.com/xiangtaokong/tgbd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.03379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03379"}},"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/xiangtaokong/mioir","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiangtaokong/tgbd","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_violates":1,"unverified":6},"by_repo_kind":{"official":{"samples":13,"ran":7,"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":13,"samples":[{"code_sha256_prefix":"e33f35a70fbf96fe","entry":"down_tensor","repo":"xiangtaokong/mioir","repo_kind":"official","path":"data_script/add_MiO_test_degradation.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/data_script/add_MiO_test_degradation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e33f35a70fbf96fe"}},{"code_sha256_prefix":"cd569444547de84f","entry":"get_position_from_periods","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/models/lr_scheduler.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/models/lr_scheduler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd569444547de84f"}},{"code_sha256_prefix":"ab4109634b75ef8b","entry":"is_image_file","repo":"xiangtaokong/mioir","repo_kind":"official","path":"data_script/gen_sub.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/data_script/gen_sub.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab4109634b75ef8b"}},{"code_sha256_prefix":"b982e472c895e0a6","entry":"resize_tensor","repo":"xiangtaokong/mioir","repo_kind":"official","path":"data_script/add_MiO_test_degradation.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/data_script/add_MiO_test_degradation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b982e472c895e0a6"}},{"code_sha256_prefix":"fc5ba23653333ada","entry":"resize_tensor","repo":"xiangtaokong/mioir","repo_kind":"official","path":"data_script/add_MiO_train_degradation.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/data_script/add_MiO_train_degradation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc5ba23653333ada"}},{"code_sha256_prefix":"d322f4e33cbbbb9a","entry":"worker","repo":"xiangtaokong/mioir","repo_kind":"official","path":"data_script/gen_sub.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/data_script/gen_sub.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d322f4e33cbbbb9a"}},{"code_sha256_prefix":"d33436d0b5032794","entry":"zero_mask","repo":"xiangtaokong/mioir","repo_kind":"official","path":"data_script/add_MiO_test_degradation.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/data_script/add_MiO_test_degradation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d33436d0b5032794"}},{"code_sha256_prefix":"fe05416387de89c6","entry":"g_path_regularize","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/losses/gan_loss.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/losses/gan_loss.py","link_basis":"harvester_set","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":"fe05416387de89c6"}},{"code_sha256_prefix":"81eb425a41a7c2a1","entry":"gradient_penalty_loss","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/losses/gan_loss.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/losses/gan_loss.py","link_basis":"harvester_set","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":"81eb425a41a7c2a1"}},{"code_sha256_prefix":"c7cba9053f3cadb5","entry":"r1_penalty","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/losses/gan_loss.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/losses/gan_loss.py","link_basis":"harvester_set","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":"c7cba9053f3cadb5"}},{"code_sha256_prefix":"a648a03a952822c0","entry":"reduce_loss","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/losses/loss_util.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/losses/loss_util.py","link_basis":"harvester_set","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":"a648a03a952822c0"}},{"code_sha256_prefix":"1ba39317ea81871a","entry":"weight_reduce_loss","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/losses/loss_util.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/losses/loss_util.py","link_basis":"harvester_set","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":"1ba39317ea81871a"}},{"code_sha256_prefix":"cf63f8afc13f62a7","entry":"weighted_loss","repo":"xiangtaokong/mioir","repo_kind":"official","path":"basicsr/losses/loss_util.py","file_url":"https://github.com/xiangtaokong/mioir/blob/HEAD/basicsr/losses/loss_util.py","link_basis":"harvester_set","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":"cf63f8afc13f62a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}