{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/divergen-improving-instance-segmentation-by","title":"DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data","arxiv_id":"2405.10185","date":"2024-05-16","proceeding":"CVPR 2024 1","authors":["Chengxiang Fan","Muzhi Zhu","Hao Chen","Yang Liu","Weijia Wu","Huaqi Zhang","Chunhua Shen"],"abstract":"Instance segmentation is data-hungry, and as model capacity increases, data scale becomes crucial for improving the accuracy. Most instance segmentation datasets today require costly manual annotation, limiting their data scale. Models trained on such data are prone to overfitting on the training set, especially for those rare categories. While recent works have delved into exploiting generative models to create synthetic datasets for data augmentation, these approaches do not efficiently harness the full potential of generative models. To address these issues, we introduce a more efficient strategy to construct generative datasets for data augmentation, termed DiverGen. Firstly, we provide an explanation of the role of generative data from the perspective of distribution discrepancy. We investigate the impact of different data on the distribution learned by the model. We argue that generative data can expand the data distribution that the model can learn, thus mitigating overfitting. Additionally, we find that the diversity of generative data is crucial for improving model performance and enhance it through various strategies, including category diversity, prompt diversity, and generative model diversity. With these strategies, we can scale the data to millions while maintaining the trend of model performance improvement. On the LVIS dataset, DiverGen significantly outperforms the strong model X-Paste, achieving +1.1 box AP and +1.1 mask AP across all categories, and +1.9 box AP and +2.5 mask AP for rare categories.","url_abs":"https://arxiv.org/abs/2405.10185v1","url_pdf":"https://arxiv.org/pdf/2405.10185v1.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":"divergen-improving-instance-segmentation-by","repo_url":"https://github.com/aim-uofa/DiverGen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","task":"Instance Segmentation","dataset":"LVIS v1.0 val","model":"DiverGen (Swin-L)","rank_in_archive_order":7,"of":25,"metrics":{"mask AP":"45.5","mask APr":"45.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-val","task":"Object Detection","dataset":"LVIS v1.0 val","model":"DiverGen (Swin-L)","rank_in_archive_order":9,"of":15,"metrics":{"box AP":"51.2","box APr":"50.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.10185","atlas_url":"https://app.syntology.ai/?focus=2405.10185","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2405.10185"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.10185\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.10185"},"call":"get_concepts_for_paper(arxiv_id=\"2405.10185\")"}],"by_repo":[{"repo":"aim-uofa/DiverGen","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.02435"],"harvested_for_calls":[{"arxiv_id":"2406.02435","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.02435"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.02435\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4586c312e344398656f81cbbf052d08c8fcf4345c3561894e09f308a7feec40a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}