{"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/correcting-deviations-from-normality-a","title":"Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection","arxiv_id":"2503.19357","date":"2025-03-25","proceeding":"CVPR 2025 1","authors":["Farzad Beizaee","Gregory A. Lodygensky","Christian Desrosiers","Jose Dolz"],"abstract":"Recent advances in diffusion models have spurred research into their application for Reconstruction-based unsupervised anomaly detection. However, these methods may struggle with maintaining structural integrity and recovering the anomaly-free content of abnormal regions, especially in multi-class scenarios. Furthermore, diffusion models are inherently designed to generate images from pure noise and struggle to selectively alter anomalous regions of an image while preserving normal ones. This leads to potential degradation of normal regions during reconstruction, hampering the effectiveness of anomaly detection. This paper introduces a reformulation of the standard diffusion model geared toward selective region alteration, allowing the accurate identification of anomalies. By modeling anomalies as noise in the latent space, our proposed \\textbf{Deviation correction diffusion} (\\Ours) model preserves the normal regions and encourages transformations exclusively on anomalous areas. This selective approach enhances the reconstruction quality, facilitating effective unsupervised detection and localization of anomaly regions. Comprehensive evaluations demonstrate the superiority of our method in accurately identifying and localizing anomalies in complex images, with pixel-level AUPRC improvements of 11-14\\% over state-of-the-art models on well known anomaly detection datasets. The code is available at https://github.com/farzad-bz/DeCo-Diff","url_abs":"https://arxiv.org/abs/2503.19357v1","url_pdf":"https://arxiv.org/pdf/2503.19357v1.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":"correcting-deviations-from-normality-a","repo_url":"https://github.com/farzad-bz/DeCo-Diff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"unsupervised-anomaly-detection","task_name":"Unsupervised Anomaly Detection"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.19357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19357"}},"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/farzad-bz/DeCo-Diff","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran_violates":2,"ran_honours":3,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":15,"ran":10,"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":"d6a68e210556f857","entry":"approx_standard_normal_cdf","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6a68e210556f857"}},{"code_sha256_prefix":"ab1c9568b4e13899","entry":"continuous_gaussian_log_likelihood","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab1c9568b4e13899"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"3e0fa4efc22272d4","entry":"get_beta_schedule","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e0fa4efc22272d4"}},{"code_sha256_prefix":"36e30c7fb679ec78","entry":"get_named_beta_schedule","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36e30c7fb679ec78"}},{"code_sha256_prefix":"f6d7c009a8efb8b7","entry":"mean_flat","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6d7c009a8efb8b7"}},{"code_sha256_prefix":"8afbfc42c6ea0448","entry":"normal_kl","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8afbfc42c6ea0448"}},{"code_sha256_prefix":"ea9dbc131adf582e","entry":"space_timesteps","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/respace.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/respace.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea9dbc131adf582e"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"ff2f7a13bff3b641","entry":"compute_pro","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"evaluation_DeCo_Diff.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/evaluation_DeCo_Diff.py","link_basis":"harvester_set","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":"ff2f7a13bff3b641"}},{"code_sha256_prefix":"8382f7e48cc8a309","entry":"create_logger","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"train_DeCo_Diff.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/train_DeCo_Diff.py","link_basis":"harvester_set","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":"8382f7e48cc8a309"}},{"code_sha256_prefix":"e48218d7d73db0b3","entry":"create_named_schedule_sampler","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"diffusion/timestep_sampler.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/diffusion/timestep_sampler.py","link_basis":"harvester_set","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":"e48218d7d73db0b3"}},{"code_sha256_prefix":"b0ea0c07e00e7309","entry":"shuffle_patches","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"train_DeCo_Diff.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/train_DeCo_Diff.py","link_basis":"harvester_set","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":"b0ea0c07e00e7309"}},{"code_sha256_prefix":"a2a7f114e201301e","entry":"smooth_mask","repo":"farzad-bz/DeCo-Diff","repo_kind":"official","path":"evaluation_DeCo_Diff.py","file_url":"https://github.com/farzad-bz/DeCo-Diff/blob/HEAD/evaluation_DeCo_Diff.py","link_basis":"harvester_set","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":"a2a7f114e201301e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}