Papers › Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation

Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation

20 Aug 2024arXiv:2408.10537archive 2025-07-28

Jiawei Han, Kaiqi Liu, Wei Li, Guangzhi Chen

Point cloud semantic segmentation can significantly enhance the perception of an intelligent agent. Nevertheless, the discriminative capability of the segmentation network is influenced by the quantity of samples available for different categories. To mitigate the cognitive bias induced by class imbalance, this paper introduces a novel method, namely subspace prototype guidance (\textbf{SPG}), to guide the training of segmentation network. Specifically, the point cloud is initially separated into independent point sets by category to provide initial conditions for the generation of feature subspaces. The auxiliary branch which consists of an encoder and a projection head maps these point sets into separate feature subspaces. Subsequently, the feature prototypes which are extracted from the current separate subspaces and then combined with prototypes of historical subspaces guide the feature space of main branch to enhance the discriminability of features of minority categories. The prototypes derived from the feature space of main branch are also employed to guide the training of the auxiliary branch, forming a supervisory loop to maintain consistent convergence of the entire network. The experiments conducted on the large public benchmarks (i.e. S3DIS, ScanNet v2, ScanNet200, Toronto-3D) and collected real-world data illustrate that the proposed method significantly improves the segmentation performance and surpasses the state-of-the-art method. The code is available at \url{https://github.com/Javion11/PointLiBR.git}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2408.10537")

Code

Syntology Ran 8 of 14 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Javion11/PointLiBR officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 8 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
2ran · fixture could not drive it
5ran
6unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Javion11/PointLiBR. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

bernoulli_mask Javion11/PointLiBR/main/main_inv.py official repository ran MIT (permissive) · 41f42919cf5b6978 · report
collate_fn Javion11/PointLiBR/openpoints/dataset/build.py official repository ran fingerprinted MIT (permissive) · f7bd8f9551547241 · report
gen_sample Javion11/PointLiBR/main/main_spg.py official repository ran MIT (permissive) · 1176105bd90f0374 · report
iou Javion11/PointLiBR/openpoints/loss/lovasz_losses.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · d94639b28b2134ff · report
iou_binary Javion11/PointLiBR/openpoints/loss/lovasz_losses.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 1211530cd527bd0b · report
lovasz_grad Javion11/PointLiBR/openpoints/loss/lovasz_losses.py official repository ran · violated contract fingerprinted MIT (permissive) · e85b5d21dc5b8382 · report
mask_target Javion11/PointLiBR/main/main_inv.py official repository ran MIT (permissive) · ebfa7541d28ada0e · report
point_collate_fn Javion11/PointLiBR/openpoints/dataset/build.py official repository ran MIT (permissive) · b7dd33a246b1c8b6 · report
download_url Javion11/PointLiBR/openpoints/dataset/data_util.py official repository unverified MIT (permissive) · 556e417290a6e1fd · report
fnv_hash_vec Javion11/PointLiBR/openpoints/dataset/data_util.py official repository unverified MIT (permissive) · 0086c892bd1df796 · report
is_model Javion11/PointLiBR/openpoints/models/registry.py official repository unverified MIT (permissive) · cd2a47ded9dd84cf · report
list_models Javion11/PointLiBR/openpoints/models/registry.py official repository unverified MIT (permissive) · d14a6ca5ff9d530e · report
ravel_hash_vec Javion11/PointLiBR/openpoints/dataset/data_util.py official repository unverified MIT (permissive) · afdc8ad15d9098b8 · report
register_model Javion11/PointLiBR/openpoints/models/registry.py official repository unverified MIT (permissive) · e13039fb1c347452 · report

Tasks

SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation S3DIS Area5 SPG(PTv2) mAcc 79.5 #13 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 SPG(PTv2) mIoU 73.3 #13 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 SPG(PTv2) oAcc 91.9 #13 of 61 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections