{"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/gpr-net-geometric-prototypical-network-for","title":"GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning","arxiv_id":"2304.06007","date":"2023-04-12","proceeding":null,"authors":["Tejas Anvekar","Dena Bazazian"],"abstract":"In the realm of 3D-computer vision applications, point cloud few-shot learning plays a critical role. However, it poses an arduous challenge due to the sparsity, irregularity, and unordered nature of the data. Current methods rely on complex local geometric extraction techniques such as convolution, graph, and attention mechanisms, along with extensive data-driven pre-training tasks. These approaches contradict the fundamental goal of few-shot learning, which is to facilitate efficient learning. To address this issue, we propose GPr-Net (Geometric Prototypical Network), a lightweight and computationally efficient geometric prototypical network that captures the intrinsic topology of point clouds and achieves superior performance. Our proposed method, IGI++ (Intrinsic Geometry Interpreter++) employs vector-based hand-crafted intrinsic geometry interpreters and Laplace vectors to extract and evaluate point cloud morphology, resulting in improved representations for FSL (Few-Shot Learning). Additionally, Laplace vectors enable the extraction of valuable features from point clouds with fewer points. To tackle the distribution drift challenge in few-shot metric learning, we leverage hyperbolic space and demonstrate that our approach handles intra and inter-class variance better than existing point cloud few-shot learning methods. Experimental results on the ModelNet40 dataset show that GPr-Net outperforms state-of-the-art methods in few-shot learning on point clouds, achieving utmost computational efficiency that is $170\\times$ better than all existing works. The code is publicly available at https://github.com/TejasAnvekar/GPr-Net.","url_abs":"https://arxiv.org/abs/2304.06007v1","url_pdf":"https://arxiv.org/pdf/2304.06007v1.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":"gpr-net-geometric-prototypical-network-for","repo_url":"https://github.com/tejasanvekar/gpr-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gpr-net-geometric-prototypical-network-for","repo_url":"https://github.com/TejasAnvekar/Mahalanobis-k-NN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"gpr","task_name":"GPR"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-3","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (10-shot)","model":"GPr-Net + Hyp (512)","rank_in_archive_order":22,"of":31,"metrics":{"Overall Accuracy":"71.6","Standard Deviation":"1.1"},"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":"GPr-Net + Hyp (1024)","rank_in_archive_order":23,"of":31,"metrics":{"Overall Accuracy":"70.4","Standard Deviation":"1.8"},"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":"GPr-Net + Euc (512)","rank_in_archive_order":24,"of":31,"metrics":{"Overall Accuracy":"62.3","Standard Deviation":"2.0"},"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":"GPr-Net + Euc (1024)","rank_in_archive_order":25,"of":31,"metrics":{"Overall Accuracy":"62.1","Standard Deviation":"1.9"},"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":"GPr-Net + Hyp (512)","rank_in_archive_order":22,"of":31,"metrics":{"Overall Accuracy":"73.8","Standard Deviation":"2.0"},"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":"GPr-Net + Hyp (1024)","rank_in_archive_order":23,"of":31,"metrics":{"Overall Accuracy":"72.8","Standard Deviation":"1.8"},"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":"GPr-Net + Euc (1024)","rank_in_archive_order":24,"of":31,"metrics":{"Overall Accuracy":"63.4","Standard Deviation":"2.0"},"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":"GPr-Net + Euc (512)","rank_in_archive_order":25,"of":31,"metrics":{"Overall Accuracy":"63.3","Standard Deviation":"2.2"},"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":"GPr-Net + Hyp (512)","rank_in_archive_order":21,"of":30,"metrics":{"Overall Accuracy":"81.1","Standard Deviation":"1.5"},"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":"GPr-Net + Hyp (1024)","rank_in_archive_order":22,"of":30,"metrics":{"Overall Accuracy":"80.4","Standard Deviation":"0.5"},"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":"GPr-Net + Euc (1024)","rank_in_archive_order":23,"of":30,"metrics":{"Overall Accuracy":"74.4","Standard Deviation":"2.0"},"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":"GPr-Net + Euc (512)","rank_in_archive_order":24,"of":30,"metrics":{"Overall Accuracy":"74.0","Standard Deviation":"2.3"},"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":"GPr-Net + Hyp (512)","rank_in_archive_order":21,"of":30,"metrics":{"Overall Accuracy":"82.7","Standard Deviation":"1.3"},"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":"GPr-Net + Hyp (1024)","rank_in_archive_order":22,"of":30,"metrics":{"Overall Accuracy":"82.0","Standard Deviation":"0.9"},"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":"GPr-Net + Euc (1024)","rank_in_archive_order":23,"of":30,"metrics":{"Overall Accuracy":"75.1","Standard Deviation":"2.1"},"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":"GPr-Net + Euc (512)","rank_in_archive_order":24,"of":30,"metrics":{"Overall Accuracy":"75.0","Standard Deviation":"2.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"tejasanvekar/gpr-net","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.02210"],"harvested_for_calls":[{"arxiv_id":"2110.02210","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.02210"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.02210\")"}]},{"repo":"TejasAnvekar/Mahalanobis-k-NN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.02210"],"harvested_for_calls":[{"arxiv_id":"2110.02210","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.02210"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.02210\")"}]}],"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":"7d24a7c51a968e15d02689279ae658a08c12011106e70511b5eb17b02fc92b0c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}