{"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/instance-aware-dynamic-prompt-tuning-for-pre","title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","arxiv_id":"2304.07221","date":"2023-04-14","proceeding":"ICCV 2023 1","authors":["Yaohua Zha","Jinpeng Wang","Tao Dai","Bin Chen","Zhi Wang","Shu-Tao Xia"],"abstract":"Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at \\url{https://github.com/zyh16143998882/ICCV23-IDPT}.","url_abs":"https://arxiv.org/abs/2304.07221v2","url_pdf":"https://arxiv.org/pdf/2304.07221v2.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":"instance-aware-dynamic-prompt-tuning-for-pre","repo_url":"https://github.com/zyh16143998882/IDPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"instance-aware-dynamic-prompt-tuning-for-pre","repo_url":"https://github.com/zyh16143998882/iccv23-idpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"instance-aware-dynamic-prompt-tuning-for-pre","repo_url":"https://github.com/zyh16143998882/aaai24-pointfemae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-parameter-efficient-fine-tuning-for","task_name":"3D Parameter-Efficient Fine-Tuning for Classification"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"visual-prompt-tuning","task_name":"Visual Prompt Tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"IDPT","rank_in_archive_order":15,"of":111,"metrics":{"Overall Accuracy":"94.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"IDPT","rank_in_archive_order":35,"of":77,"metrics":{"OBJ-BG (OA)":"93.12","Overall Accuracy":"88.51"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-3","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (10-shot)","model":"IDPT","rank_in_archive_order":12,"of":31,"metrics":{"Overall Accuracy":"92.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-4","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (20-shot)","model":"IDPT","rank_in_archive_order":13,"of":31,"metrics":{"Overall Accuracy":"95.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-1","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (10-shot)","model":"IDPT","rank_in_archive_order":9,"of":30,"metrics":{"Overall Accuracy":"97.3"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-2","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (20-shot)","model":"IDPT","rank_in_archive_order":14,"of":30,"metrics":{"Overall Accuracy":"97.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.07221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.07221"}},"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/zyh16143998882/iccv23-idpt","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zyh16143998882/IDPT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zyh16143998882/aaai24-pointfemae","reach":null}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":7,"repositories":1},"listed":{"samples":4,"ran":2,"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":14,"samples":[{"code_sha256_prefix":"e50a82843946d9b4","entry":"Block","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e50a82843946d9b4"}},{"code_sha256_prefix":"3310d0089f97cac4","entry":"BlockH","repo":"zyh16143998882/aaai24-pointfemae","repo_kind":"listed","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/aaai24-pointfemae/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3310d0089f97cac4"}},{"code_sha256_prefix":"50a5714aab590a59","entry":"DGCNNView","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50a5714aab590a59"}},{"code_sha256_prefix":"f9673b64dec8e89c","entry":"DGCNNViewLight2","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9673b64dec8e89c"}},{"code_sha256_prefix":"c7b64faa053f3761","entry":"DGCNNViewMLP","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7b64faa053f3761"}},{"code_sha256_prefix":"892fce57c8dde09f","entry":"LEM","repo":"zyh16143998882/aaai24-pointfemae","repo_kind":"listed","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/aaai24-pointfemae/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"892fce57c8dde09f"}},{"code_sha256_prefix":"cc1832f8e8b3aa69","entry":"Mlp","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc1832f8e8b3aa69"}},{"code_sha256_prefix":"bb22f81886c8963d","entry":"TransformerEncoder","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb22f81886c8963d"}},{"code_sha256_prefix":"ed4cd8f3b2b83784","entry":"act_layer","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed4cd8f3b2b83784"}},{"code_sha256_prefix":"c87e47714f68fa7d","entry":"DGCNNViewLight","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c87e47714f68fa7d"}},{"code_sha256_prefix":"804ab252335f0df6","entry":"MaskTransformerH","repo":"zyh16143998882/aaai24-pointfemae","repo_kind":"listed","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/aaai24-pointfemae/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"804ab252335f0df6"}},{"code_sha256_prefix":"2ede111e17f38a68","entry":"TransFormerLayerView","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ede111e17f38a68"}},{"code_sha256_prefix":"05089574e956e053","entry":"TransformerEncoderH","repo":"zyh16143998882/aaai24-pointfemae","repo_kind":"listed","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/aaai24-pointfemae/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"05089574e956e053"}},{"code_sha256_prefix":"b653db8db6d0a32f","entry":"TransformerPromptEncoderLayerI","repo":"zyh16143998882/IDPT","repo_kind":"official","path":"models/Point_MAE.py","file_url":"https://github.com/zyh16143998882/IDPT/blob/HEAD/models/Point_MAE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b653db8db6d0a32f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}