{"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/pointlora-low-rank-adaptation-with-token-1","title":"PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning","arxiv_id":"2504.16023","date":"2025-04-22","proceeding":"CVPR 2025 1","authors":["Song Wang","Xiaolu Liu","Lingdong Kong","Jianyun Xu","Chunyong Hu","Gongfan Fang","Wentong Li","Jianke Zhu","Xinchao Wang"],"abstract":"Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained models grow in complexity, fully fine-tuning them for downstream applications demands substantial computational and storage resources. Parameter-efficient fine-tuning (PEFT) methods offer a promising solution to mitigate these resource requirements, yet most current approaches rely on complex adapter and prompt mechanisms that increase tunable parameters. In this paper, we propose PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models. Our approach embeds LoRA layers within the most parameter-intensive components of point cloud transformers, reducing the need for tunable parameters while enhancing global feature capture. Additionally, multi-scale token selection extracts critical local information to serve as prompts for downstream fine-tuning, effectively complementing the global context captured by LoRA. The experimental results across various pre-trained models and three challenging public datasets demonstrate that our approach achieves competitive performance with only 3.43% of the trainable parameters, making it highly effective for resource-constrained applications. Source code is available at: https://github.com/songw-zju/PointLoRA.","url_abs":"https://arxiv.org/abs/2504.16023v2","url_pdf":"https://arxiv.org/pdf/2504.16023v2.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":"pointlora-low-rank-adaptation-with-token-1","repo_url":"https://github.com/songw-zju/pointlora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.16023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16023"}},"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/songw-zju/pointlora","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/songw-zju/PointLoRA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":10,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"39b2b4edb312a41a","entry":"load_modelnet_data","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39b2b4edb312a41a"}},{"code_sha256_prefix":"d65f58435eedf5a5","entry":"merge_new_config","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d65f58435eedf5a5"}},{"code_sha256_prefix":"4783fbece52f500e","entry":"pc_normalize","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4783fbece52f500e"}},{"code_sha256_prefix":"91ac3709882c1072","entry":"cfg_from_yaml_file","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91ac3709882c1072"}},{"code_sha256_prefix":"f80066a00e7156a2","entry":"farthest_point_sample","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"datasets/ModelNetDataset.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/datasets/ModelNetDataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f80066a00e7156a2"}},{"code_sha256_prefix":"14029b06371b000c","entry":"gather_tensor","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/dist_utils.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/dist_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14029b06371b000c"}},{"code_sha256_prefix":"90328f69a5a05f77","entry":"get_config","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90328f69a5a05f77"}},{"code_sha256_prefix":"79cfc5c7bcc39b7b","entry":"get_missing_parameters_message","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/checkpoint.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79cfc5c7bcc39b7b"}},{"code_sha256_prefix":"f45b84cf72162235","entry":"get_unexpected_parameters_message","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/checkpoint.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f45b84cf72162235"}},{"code_sha256_prefix":"5f9ab5e0087e7f19","entry":"reduce_tensor","repo":"songw-zju/PointLoRA","repo_kind":"official","path":"utils/dist_utils.py","file_url":"https://github.com/songw-zju/PointLoRA/blob/HEAD/utils/dist_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f9ab5e0087e7f19"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}