{"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/few-shot-defect-image-generation-based-on","title":"Few-shot Defect Image Generation based on Consistency Modeling","arxiv_id":"2408.00372","date":"2024-08-01","proceeding":null,"authors":["Qingfeng Shi","Jing Wei","Fei Shen","Zhengtao Zhang"],"abstract":"Image generation can solve insufficient labeled data issues in defect detection. Most defect generation methods are only trained on a single product without considering the consistencies among multiple products, leading to poor quality and diversity of generated results. To address these issues, we propose DefectDiffu, a novel text-guided diffusion method to model both intra-product background consistency and inter-product defect consistency across multiple products and modulate the consistency perturbation directions to control product type and defect strength, achieving diversified defect image generation. Firstly, we leverage a text encoder to separately provide consistency prompts for background, defect, and fusion parts of the disentangled integrated architecture, thereby disentangling defects and normal backgrounds. Secondly, we propose the double-free strategy to generate defect images through two-stage perturbation of consistency direction, thereby controlling product type and defect strength by adjusting the perturbation scale. Besides, DefectDiffu can generate defect mask annotations utilizing cross-attention maps from the defect part. Finally, to improve the generation quality of small defects and masks, we propose the adaptive attention-enhance loss to increase the attention to defects. Experimental results demonstrate that DefectDiffu surpasses state-of-the-art methods in terms of generation quality and diversity, thus effectively improving downstream defection performance. Moreover, defect perturbation directions can be transferred among various products to achieve zero-shot defect generation, which is highly beneficial for addressing insufficient data issues. The code are available at https://github.com/FFDD-diffusion/DefectDiffu.","url_abs":"https://arxiv.org/abs/2408.00372v1","url_pdf":"https://arxiv.org/pdf/2408.00372v1.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":"few-shot-defect-image-generation-based-on","repo_url":"https://github.com/ffdd-diffusion/defectdiffu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"defect-detection","task_name":"Defect Detection"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.00372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00372"}},"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/ffdd-diffusion/defectdiffu","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":9,"ran_honours":4,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":19,"ran":14,"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":19,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"autoencoder.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/autoencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"d6a68e210556f857","entry":"approx_standard_normal_cdf","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d6a68e210556f857"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"ab1c9568b4e13899","entry":"continuous_gaussian_log_likelihood","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab1c9568b4e13899"}},{"code_sha256_prefix":"c92c27c924b517e8","entry":"get_2d_sincos_pos_embed","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"models_add_cross_concate.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/models_add_cross_concate.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c92c27c924b517e8"}},{"code_sha256_prefix":"3e0fa4efc22272d4","entry":"get_beta_schedule","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e0fa4efc22272d4"}},{"code_sha256_prefix":"36e30c7fb679ec78","entry":"get_named_beta_schedule","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"36e30c7fb679ec78"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"f6d7c009a8efb8b7","entry":"mean_flat","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6d7c009a8efb8b7"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"models_add_cross_concate.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/models_add_cross_concate.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"autoencoder.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/autoencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"8afbfc42c6ea0448","entry":"normal_kl","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8afbfc42c6ea0448"}},{"code_sha256_prefix":"ea9dbc131adf582e","entry":"space_timesteps","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/respace.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea9dbc131adf582e"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"39e6b23b55f376ea","entry":"build_model","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/clip/model.py","link_basis":"harvester_set","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":"39e6b23b55f376ea"}},{"code_sha256_prefix":"e48218d7d73db0b3","entry":"create_named_schedule_sampler","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"diffusion/timestep_sampler.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e48218d7d73db0b3"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"models_add_cross_concate.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/models_add_cross_concate.py","link_basis":"harvester_set","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":"665d8a4e8f673a4c"}},{"code_sha256_prefix":"f6f30e41636ae569","entry":"load","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/clip/clip.py","link_basis":"plan_row","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":"f6f30e41636ae569"}},{"code_sha256_prefix":"f97adc1ae5efb785","entry":"make_attn","repo":"ffdd-diffusion/defectdiffu","repo_kind":"official","path":"autoencoder.py","file_url":"https://github.com/ffdd-diffusion/defectdiffu/blob/HEAD/autoencoder.py","link_basis":"harvester_set","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":"f97adc1ae5efb785"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}