{"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/dataset-diffusion-diffusion-based-synthetic","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","arxiv_id":"2309.14303","date":"2023-09-25","proceeding":null,"authors":["Quang Nguyen","Truong Vu","Anh Tran","Khoi Nguyen"],"abstract":"Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category labels, we propose a novel method for generating pixel-level semantic segmentation labels using the text-to-image generative model Stable Diffusion (SD). By utilizing the text prompts, cross-attention, and self-attention of SD, we introduce three new techniques: class-prompt appending, class-prompt cross-attention, and self-attention exponentiation. These techniques enable us to generate segmentation maps corresponding to synthetic images. These maps serve as pseudo-labels for training semantic segmenters, eliminating the need for labor-intensive pixel-wise annotation. To account for the imperfections in our pseudo-labels, we incorporate uncertainty regions into the segmentation, allowing us to disregard loss from those regions. We conduct evaluations on two datasets, PASCAL VOC and MSCOCO, and our approach significantly outperforms concurrent work. Our benchmarks and code will be released at https://github.com/VinAIResearch/Dataset-Diffusion","url_abs":"https://arxiv.org/abs/2309.14303v4","url_pdf":"https://arxiv.org/pdf/2309.14303v4.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":"dataset-diffusion-diffusion-based-synthetic","repo_url":"https://github.com/vinairesearch/dataset-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"dataset-generation","task_name":"Dataset Generation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.14303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14303"}},"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/VinAIResearch/Dataset-Diffusion","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vinairesearch/dataset-diffusion","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":10,"samples":[{"code_sha256_prefix":"4c4e41748bf35619","entry":"AttentionStoreClassPrompts","repo":"vinairesearch/dataset-diffusion","repo_kind":"official","path":"src/attn_processor.py","file_url":"https://github.com/vinairesearch/dataset-diffusion/blob/HEAD/src/attn_processor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4c4e41748bf35619"}},{"code_sha256_prefix":"bdc53ede381a35c8","entry":"aggregate_attention","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"src/attn_processor.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/src/attn_processor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bdc53ede381a35c8"}},{"code_sha256_prefix":"a669df2cd07c07bb","entry":"calculate_file_sha256","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"mmsegmentation/.dev/gather_models.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/mmsegmentation/.dev/gather_models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a669df2cd07c07bb"}},{"code_sha256_prefix":"b8bb3de40cf61c64","entry":"dump_yaml_and_check_difference","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"mmsegmentation/.dev/update_model_index.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/mmsegmentation/.dev/update_model_index.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b8bb3de40cf61c64"}},{"code_sha256_prefix":"b9e0b82131912b70","entry":"get_collection_name_list","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"mmsegmentation/.dev/update_model_index.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/mmsegmentation/.dev/update_model_index.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b9e0b82131912b70"}},{"code_sha256_prefix":"88d68650d669bb11","entry":"get_final_iter","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"mmsegmentation/.dev/gather_models.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/mmsegmentation/.dev/gather_models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"88d68650d669bb11"}},{"code_sha256_prefix":"b00babc7ee422677","entry":"get_indices","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"src/datasets/coco.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/src/datasets/coco.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b00babc7ee422677"}},{"code_sha256_prefix":"4037fd6bcb9ca210","entry":"process_checkpoint","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"mmsegmentation/.dev/gather_models.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/mmsegmentation/.dev/gather_models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4037fd6bcb9ca210"}},{"code_sha256_prefix":"78abe63d4c5a0e57","entry":"AttentionControl","repo":"vinairesearch/dataset-diffusion","repo_kind":"official","path":"src/attn_processor.py","file_url":"https://github.com/vinairesearch/dataset-diffusion/blob/HEAD/src/attn_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"78abe63d4c5a0e57"}},{"code_sha256_prefix":"f6d863d51f58002a","entry":"get_model_info","repo":"VinAIResearch/Dataset-Diffusion","repo_kind":"official","path":"mmsegmentation/.dev/update_model_index.py","file_url":"https://github.com/VinAIResearch/Dataset-Diffusion/blob/HEAD/mmsegmentation/.dev/update_model_index.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f6d863d51f58002a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}