{"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/style-aware-normalized-loss-for-improving","title":"Style-Aware Normalized Loss for Improving Arbitrary Style Transfer","arxiv_id":"2104.10064","date":"2021-04-18","proceeding":"CVPR 2021 1","authors":["Jiaxin Cheng","Ayush Jaiswal","Yue Wu","Pradeep Natarajan","Prem Natarajan"],"abstract":"Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST). Although appealing results have been widely reported in literature, our empirical studies on four well-known AST approaches (GoogleMagenta, AdaIN, LinearTransfer, and SANet) show that more than 50% of the time, AST stylized images are not acceptable to human users, typically due to under- or over-stylization. We systematically study the cause of this imbalanced style transferability (IST) and propose a simple yet effective solution to mitigate this issue. Our studies show that the IST issue is related to the conventional AST style loss, and reveal that the root cause is the equal weightage of training samples irrespective of the properties of their corresponding style images, which biases the model towards certain styles. Through investigation of the theoretical bounds of the AST style loss, we propose a new loss that largely overcomes IST. Theoretical analysis and experimental results validate the effectiveness of our loss, with over 80% relative improvement in style deception rate and 98% relatively higher preference in human evaluation.","url_abs":"https://arxiv.org/abs/2104.10064v1","url_pdf":"https://arxiv.org/pdf/2104.10064v1.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":"style-aware-normalized-loss-for-improving","repo_url":"https://github.com/Neroxn/Style-Aware-Normalized/tree/main/Project_Kargi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.10064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10064"}},"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":"deterministic:regex_extraction","url":"https://github.com/inejc/painters","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"found_in_text":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"2a24c78da9f911c5","entry":"apply_to_images_in_subdirs","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/data_provider.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/data_provider.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":"2a24c78da9f911c5"}},{"code_sha256_prefix":"204b60976bc2c75c","entry":"compile_model","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/train_cnn.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/train_cnn.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":"204b60976bc2c75c"}},{"code_sha256_prefix":"2ebc63f5bd35cd47","entry":"load_img_arr","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/utils.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/utils.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":"2ebc63f5bd35cd47"}},{"code_sha256_prefix":"34297d34ed94c50c","entry":"load_pickle","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/utils.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/utils.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":"34297d34ed94c50c"}},{"code_sha256_prefix":"b80fc92d6edfc5bc","entry":"load_trained_cnn_feature_maps_layer","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/train_cnn.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/train_cnn.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":"b80fc92d6edfc5bc"}},{"code_sha256_prefix":"244fa294b0dabbf2","entry":"load_trained_cnn_penultimate_layer","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/train_cnn.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/train_cnn.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":"244fa294b0dabbf2"}},{"code_sha256_prefix":"d9397cebf67848e7","entry":"read_lines","repo":"inejc/painters","repo_kind":"found_in_text","path":"painters/utils.py","file_url":"https://github.com/inejc/painters/blob/HEAD/painters/utils.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":"d9397cebf67848e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}