{"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/entropy-driven-sampling-and-training-scheme","title":"Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation","arxiv_id":"2206.11474","date":"2022-06-23","proceeding":null,"authors":["Shengming Li","Guangcong Zheng","Hui Wang","Taiping Yao","Yang Chen","Shoudong Ding","Xi Li"],"abstract":"Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time step of denoising process. However, due to the ability of classifier to easily discriminate an incompletely generated image only with high-level structure, the gradient, which is a kind of class information guidance, tends to vanish early, leading to the collapse from conditional generation process into the unconditional process. To address this problem, we propose two simple but effective approaches from two perspectives. For sampling procedure, we introduce the entropy of predicted distribution as the measure of guidance vanishing level and propose an entropy-aware scaling method to adaptively recover the conditional semantic guidance. For training stage, we propose the entropy-aware optimization objectives to alleviate the overconfident prediction for noisy data.On ImageNet1000 256x256, with our proposed sampling scheme and trained classifier, the pretrained conditional and unconditional DDPM model can achieve 10.89% (4.59 to 4.09) and 43.5% (12 to 6.78) FID improvement respectively. The code is available at https://github.com/ZGCTroy/ED-DPM.","url_abs":"https://arxiv.org/abs/2206.11474v5","url_pdf":"https://arxiv.org/pdf/2206.11474v5.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":"entropy-driven-sampling-and-training-scheme","repo_url":"https://github.com/ZGCTroy/ED-DPM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"denoising","task_name":"Denoising"},{"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-imagenet","task":"Conditional Image Generation","dataset":"ImageNet 128x128","model":"ADM-G + EDS (ED-DPM, classifier_scale=0.4)","rank_in_archive_order":2,"of":22,"metrics":{"FID":"2.63","Inception score":"159.72"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet","task":"Conditional Image Generation","dataset":"ImageNet 128x128","model":"ADM-G + EDS + ECT (ED-DPM, classifier_scale=0.6)","rank_in_archive_order":3,"of":22,"metrics":{"FID":"2.68","Inception score":"169.24"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet-2","task":"Conditional Image Generation","dataset":"ImageNet 256x256","model":"ADM-G + EDS + ECT (ED-DPM, classifier_scale=1.0)","rank_in_archive_order":2,"of":5,"metrics":{"FID":"4.09","Inception score":"221.57"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"ADM-G + EDS (ED-DPM, classifier_scale=0.75)","rank_in_archive_order":79,"of":94,"metrics":{"FID":"3.96"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"ADM-G + EDS + ECT (ED-DPM, classifier_scale=1.0)","rank_in_archive_order":81,"of":94,"metrics":{"FID":"4.09"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.11474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11474"}},"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/ZGCTroy/ED-DPM","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"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":"8823499eee54f0ff","entry":"GaussianDiffusion","repo":"ZGCTroy/ED-DPM","repo_kind":"official","path":"entropy_driven_guided_diffusion/gaussian_diffusion.py","file_url":"https://github.com/ZGCTroy/ED-DPM/blob/HEAD/entropy_driven_guided_diffusion/gaussian_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8823499eee54f0ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}