{"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/cleandift-diffusion-features-without-noise","title":"CleanDIFT: Diffusion Features without Noise","arxiv_id":"2412.03439","date":"2024-12-04","proceeding":"CVPR 2025 1","authors":["Nick Stracke","Stefan Andreas Baumann","Kolja Bauer","Frank Fundel","Björn Ommer"],"abstract":"Internal features from large-scale pre-trained diffusion models have recently been established as powerful semantic descriptors for a wide range of downstream tasks. Works that use these features generally need to add noise to images before passing them through the model to obtain the semantic features, as the models do not offer the most useful features when given images with little to no noise. We show that this noise has a critical impact on the usefulness of these features that cannot be remedied by ensembling with different random noises. We address this issue by introducing a lightweight, unsupervised fine-tuning method that enables diffusion backbones to provide high-quality, noise-free semantic features. We show that these features readily outperform previous diffusion features by a wide margin in a wide variety of extraction setups and downstream tasks, offering better performance than even ensemble-based methods at a fraction of the cost.","url_abs":"https://arxiv.org/abs/2412.03439v1","url_pdf":"https://arxiv.org/pdf/2412.03439v1.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":"cleandift-diffusion-features-without-noise","repo_url":"https://github.com/CompVis/cleandift","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"GeoAware-SC + CleanDIFT (Zero-Shot)","rank_in_archive_order":5,"of":22,"metrics":{"PCK":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"SD+DINO + CleanDIFT (Zero-Shot)","rank_in_archive_order":7,"of":22,"metrics":{"PCK":"64.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"DIFT + CleanDIFT (Zero-Shot)","rank_in_archive_order":10,"of":22,"metrics":{"PCK":"61.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.03439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03439"}},"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/CompVis/cleandift","reach":{"status":"ok"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"f52ee5efbe477940","entry":"dict_to","repo":"CompVis/cleandift","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/CompVis/cleandift/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"f52ee5efbe477940"}},{"code_sha256_prefix":"c66218aaa615d85c","entry":"linear_swiglu","repo":"CompVis/cleandift","repo_kind":"official","path":"src/layers.py","file_url":"https://github.com/CompVis/cleandift/blob/HEAD/src/layers.py","link_basis":"first_harvest_node","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":"c66218aaa615d85c"}},{"code_sha256_prefix":"740ad3754ea31e72","entry":"load_image","repo":"CompVis/cleandift","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/CompVis/cleandift/blob/HEAD/src/dataloader.py","link_basis":"first_harvest_node","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":"740ad3754ea31e72"}},{"code_sha256_prefix":"08f217b424cf126d","entry":"rms_norm","repo":"CompVis/cleandift","repo_kind":"official","path":"src/layers.py","file_url":"https://github.com/CompVis/cleandift/blob/HEAD/src/layers.py","link_basis":"first_harvest_node","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":"08f217b424cf126d"}},{"code_sha256_prefix":"f77f674b4dd20ec9","entry":"zero_init","repo":"CompVis/cleandift","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/CompVis/cleandift/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"f77f674b4dd20ec9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}