{"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-diffusion-autoencoders-are-unified","title":"Denoising Diffusion Autoencoders are Unified Self-supervised Learners","arxiv_id":"2303.09769","date":"2023-03-17","proceeding":"ICCV 2023 1","authors":["Weilai Xiang","Hongyu Yang","Di Huang","Yunhong Wang"],"abstract":"Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners: by pre-training on unconditional image generation, DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders, thus making diffusion pre-training emerge as a general approach for generative-and-discriminative dual learning. To validate this, we conduct linear probe and fine-tuning evaluations. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet, respectively, and is comparable to contrastive learning and masked autoencoders for the first time. Transfer learning from ImageNet also confirms the suitability of DDAE for Vision Transformers, suggesting the potential to scale DDAEs as unified foundation models. Code is available at github.com/FutureXiang/ddae.","url_abs":"https://arxiv.org/abs/2303.09769v2","url_pdf":"https://arxiv.org/pdf/2303.09769v2.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-diffusion-autoencoders-are-unified","repo_url":"https://github.com/futurexiang/ddae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.09769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09769"}},"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/futurexiang/ddae","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/FutureXiang/ddae","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"6cf05b67ae5d93f8","entry":"DDPM","repo":"FutureXiang/ddae","repo_kind":"official","path":"model/DDPM.py","file_url":"https://github.com/FutureXiang/ddae/blob/HEAD/model/DDPM.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":"6cf05b67ae5d93f8"}},{"code_sha256_prefix":"6dea3711db7301ac","entry":"linear_beta_schedule","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6dea3711db7301ac"}},{"code_sha256_prefix":"2d0a8e4259529a17","entry":"schedules","repo":"FutureXiang/ddae","repo_kind":"official","path":"model/DDPM.py","file_url":"https://github.com/FutureXiang/ddae/blob/HEAD/model/DDPM.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d0a8e4259529a17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}