{"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/towards-large-scale-3d-representation","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","arxiv_id":"2308.09718","date":"2023-08-18","proceeding":"CVPR 2024 1","authors":["Xiaoyang Wu","Zhuotao Tian","Xin Wen","Bohao Peng","Xihui Liu","Kaicheng Yu","Hengshuang Zhao"],"abstract":"The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of large-scale 3D datasets. Merging multiple available data sources and letting them collaboratively train a single model is a potential solution. However, due to the large domain gap between 3D point cloud datasets, such mixed supervision could adversely affect the model's performance and lead to degenerated performance (i.e., negative transfer) compared to single-dataset training. In view of this challenge, we introduce Point Prompt Training (PPT), a novel framework for multi-dataset synergistic learning in the context of 3D representation learning that supports multiple pre-training paradigms. Based on this framework, we propose Prompt-driven Normalization, which adapts the model to different datasets with domain-specific prompts and Language-guided Categorical Alignment that decently unifies the multiple-dataset label spaces by leveraging the relationship between label text. Extensive experiments verify that PPT can overcome the negative transfer associated with synergistic learning and produce generalizable representations. Notably, it achieves state-of-the-art performance on each dataset using a single weight-shared model with supervised multi-dataset training. Moreover, when served as a pre-training framework, it outperforms other pre-training approaches regarding representation quality and attains remarkable state-of-the-art performance across over ten diverse downstream tasks spanning both indoor and outdoor 3D scenarios.","url_abs":"https://arxiv.org/abs/2308.09718v2","url_pdf":"https://arxiv.org/pdf/2308.09718v2.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":"towards-large-scale-3d-representation","repo_url":"https://github.com/Pointcept/Pointcept","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-scannet200","task":"3D Semantic Segmentation","dataset":"ScanNet200","model":"PPT+SparseUNet","rank_in_archive_order":12,"of":16,"metrics":{"test mIoU":"33.2","val mIoU":"31.9"},"uses_additional_data":true},{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"PPT+SparseUNet","rank_in_archive_order":42,"of":45,"metrics":{"val mIoU":"71.4%"},"uses_additional_data":true},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"PPT+SparseUNet","rank_in_archive_order":35,"of":36,"metrics":{"val mIoU":"0.786"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"PPT + SparseUNet","rank_in_archive_order":6,"of":54,"metrics":{"Mean IoU":"78.1","Number of params":"N/A","mAcc":"85.4","oAcc":"92.2"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"PPT + SparseUNet","rank_in_archive_order":16,"of":61,"metrics":{"Number of params":"N/A","mAcc":"78.2","mIoU":"72.7","oAcc":"91.5"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-scannet","task":"Semantic Segmentation","dataset":"ScanNet","model":"PPT + SparseUNet","rank_in_archive_order":12,"of":45,"metrics":{"test mIoU":"76.6","val mIoU":"76.4"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.09718","atlas_url":"https://app.syntology.ai/?focus=2308.09718","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":"2308.09718"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.09718\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.09718"},"call":"get_concepts_for_paper(arxiv_id=\"2308.09718\")"}],"by_repo":[{"repo":"Pointcept/Pointcept","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.16429"],"harvested_for_calls":[{"arxiv_id":"2503.16429","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.16429"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.16429\")"}]}],"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":"67cc0e8c75b87288db645016367e6b7141e64c6dc1f1908ca4c97c8092a97e50","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}