{"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/mosaicfusion-diffusion-models-as-data","title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation","arxiv_id":"2309.13042","date":"2023-09-22","proceeding":null,"authors":["Jiahao Xie","Wei Li","Xiangtai Li","Ziwei Liu","Yew Soon Ong","Chen Change Loy"],"abstract":"We present MosaicFusion, a simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. Our method is training-free and does not rely on any label supervision. Two key designs enable us to employ an off-the-shelf text-to-image diffusion model as a useful dataset generator for object instances and mask annotations. First, we divide an image canvas into several regions and perform a single round of diffusion process to generate multiple instances simultaneously, conditioning on different text prompts. Second, we obtain corresponding instance masks by aggregating cross-attention maps associated with object prompts across layers and diffusion time steps, followed by simple thresholding and edge-aware refinement processing. Without bells and whistles, our MosaicFusion can produce a significant amount of synthetic labeled data for both rare and novel categories. Experimental results on the challenging LVIS long-tailed and open-vocabulary benchmarks demonstrate that MosaicFusion can significantly improve the performance of existing instance segmentation models, especially for rare and novel categories. Code: https://github.com/Jiahao000/MosaicFusion.","url_abs":"https://arxiv.org/abs/2309.13042v2","url_pdf":"https://arxiv.org/pdf/2309.13042v2.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":"mosaicfusion-diffusion-models-as-data","repo_url":"https://github.com/jiahao000/mosaicfusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.13042","atlas_url":"https://app.syntology.ai/?focus=2309.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13042"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jiahao000/mosaicfusion","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"3a852035d04246db","entry":"diffusion_step","repo":"jiahao000/mosaicfusion","repo_kind":"official","path":"mosaicfusion/utils.py","file_url":"https://github.com/jiahao000/mosaicfusion/blob/HEAD/mosaicfusion/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3a852035d04246db"}},{"code_sha256_prefix":"04c4101fccb5c55b","entry":"get_valid_idx","repo":"jiahao000/mosaicfusion","repo_kind":"official","path":"mosaicfusion/bilateral_solver.py","file_url":"https://github.com/jiahao000/mosaicfusion/blob/HEAD/mosaicfusion/bilateral_solver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"04c4101fccb5c55b"}},{"code_sha256_prefix":"4284f83d10a872ab","entry":"init_latent","repo":"jiahao000/mosaicfusion","repo_kind":"official","path":"mosaicfusion/utils.py","file_url":"https://github.com/jiahao000/mosaicfusion/blob/HEAD/mosaicfusion/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4284f83d10a872ab"}},{"code_sha256_prefix":"ec22a04e890fb286","entry":"rgb2yuv","repo":"jiahao000/mosaicfusion","repo_kind":"official","path":"mosaicfusion/bilateral_solver.py","file_url":"https://github.com/jiahao000/mosaicfusion/blob/HEAD/mosaicfusion/bilateral_solver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ec22a04e890fb286"}},{"code_sha256_prefix":"5d9850cf710de517","entry":"yuv2rgb","repo":"jiahao000/mosaicfusion","repo_kind":"official","path":"mosaicfusion/bilateral_solver.py","file_url":"https://github.com/jiahao000/mosaicfusion/blob/HEAD/mosaicfusion/bilateral_solver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5d9850cf710de517"}},{"code_sha256_prefix":"9760d444d9e268d6","entry":"latent2image","repo":"jiahao000/mosaicfusion","repo_kind":"official","path":"mosaicfusion/utils.py","file_url":"https://github.com/jiahao000/mosaicfusion/blob/HEAD/mosaicfusion/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9760d444d9e268d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}