{"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/denoising-likelihood-score-matching-for-1","title":"Denoising Likelihood Score Matching for Conditional Score-based Data Generation","arxiv_id":"2203.14206","date":"2022-03-27","proceeding":"ICLR 2022 4","authors":["Chen-Hao Chao","Wei-Fang Sun","Bo-Wun Cheng","Yi-Chen Lo","Chia-Che Chang","Yu-Lun Liu","Yu-Lin Chang","Chia-Ping Chen","Chun-Yi Lee"],"abstract":"Many existing conditional score-based data generation methods utilize Bayes' theorem to decompose the gradients of a log posterior density into a mixture of scores. These methods facilitate the training procedure of conditional score models, as a mixture of scores can be separately estimated using a score model and a classifier. However, our analysis indicates that the training objectives for the classifier in these methods may lead to a serious score mismatch issue, which corresponds to the situation that the estimated scores deviate from the true ones. Such an issue causes the samples to be misled by the deviated scores during the diffusion process, resulting in a degraded sampling quality. To resolve it, we formulate a novel training objective, called Denoising Likelihood Score Matching (DLSM) loss, for the classifier to match the gradients of the true log likelihood density. Our experimental evidence shows that the proposed method outperforms the previous methods on both Cifar-10 and Cifar-100 benchmarks noticeably in terms of several key evaluation metrics. We thus conclude that, by adopting DLSM, the conditional scores can be accurately modeled, and the effect of the score mismatch issue is alleviated.","url_abs":"https://arxiv.org/abs/2203.14206v1","url_pdf":"https://arxiv.org/pdf/2203.14206v1.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":"denoising-likelihood-score-matching-for-1","repo_url":"https://github.com/chen-hao-chao/dlsm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"denoising-likelihood-score-matching-for-1","repo_url":"https://github.com/chen-hao-chao/dlsm-toy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10","task":"Conditional Image Generation","dataset":"CIFAR-10","model":"DLSM","rank_in_archive_order":2,"of":25,"metrics":{"FID":"2.25","Inception score":"9.90"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-cifar-100","task":"Conditional Image Generation","dataset":"CIFAR-100","model":"DLSM","rank_in_archive_order":1,"of":7,"metrics":{"FID":"3.86","Inception Score":"11.62"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.14206","atlas_url":"https://app.syntology.ai/?focus=2203.14206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14206"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/chen-hao-chao/dlsm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chen-hao-chao/dlsm-toy","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":"751d3edb7f661ebb","entry":"get_sde_classifier_loss_fn","repo":"chen-hao-chao/dlsm","repo_kind":"official","path":"losses.py","file_url":"https://github.com/chen-hao-chao/dlsm/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"751d3edb7f661ebb"}},{"code_sha256_prefix":"53dc165d11a003f8","entry":"get_step_fn","repo":"chen-hao-chao/dlsm-toy","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/chen-hao-chao/dlsm-toy/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53dc165d11a003f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}