Papers › Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

1 Mar 2024CVPR 2024 1arXiv:2403.00592archive 2025-07-28

Zhaochong An, Guolei Sun, Yun Liu, Fayao Liu, Zongwei Wu, Dan Wang, Luc van Gool, Serge Belongie

This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS), with a focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. The former arises from non-uniform point sampling, allowing models to distinguish the density disparities between foreground and background for easier segmentation. The latter results from sampling only 2,048 points, limiting semantic information and deviating from the real-world practice. To address these issues, we introduce a standardized FS-PCS setting, upon which a new benchmark is built. Moreover, we propose a novel FS-PCS model. While previous methods are based on feature optimization by mainly refining support features to enhance prototypes, our method is based on correlation optimization, referred to as Correlation Optimization Segmentation (COSeg). Specifically, we compute Class-specific Multi-prototypical Correlation (CMC) for each query point, representing its correlations to category prototypes. Then, we propose the Hyper Correlation Augmentation (HCA) module to enhance CMC. Furthermore, tackling the inherent property of few-shot training to incur base susceptibility for models, we propose to learn non-parametric prototypes for the base classes during training. The learned base prototypes are used to calibrate correlations for the background class through a Base Prototypes Calibration (BPC) module. Experiments on popular datasets demonstrate the superiority of COSeg over existing methods. The code is available at: https://github.com/ZhaochongAn/COSeg

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (3 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zhaochongan/coseg officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 16 samples, 10 ran (7 instrument-failed) · 6 unverified 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

16 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
6ran · our draft was wrong
1ran; the contract check could not run
1ran
6unverified

Licence: 16 of the 16 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 zhaochongan/coseg. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zhaochongan/coseg official repository 16 samples, 10 ran (7 instrument-failed) · 6 unverified
collate_fn in 500 papers util/data_util.py ran · our draft was wrong licence not identified · pointer only · a8ff948bb3cab6fd · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
collate_fn_limit_fs util/data_util.py ran · our draft was wrong licence not identified · pointer only · cba5e0e87ac98a87 · report fixture: signature batch:list/1/tuple, include_scene_names:bool/0/bool · returned tuple · level recorded 2026-09-24
collate_fn_limit_fs_train util/data_util.py ran · our draft was wrong licence not identified · pointer only · 54d071dd22199b3d · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
elu_feature_map in 14 papers model/common.py ran · honoured contract fingerprinted no licence file found · pointer only · 0d5505bd782b4a89 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_indice_pairs model/stratified_transformer.py ran licence not identified · pointer only · 0ae5d1534c27c4af · report fixture: signature p2v_map:Tensor/2/int, counts:Tensor/1/int, new_p2v_map:Tensor/2/int, new_counts:Tensor/1/int, downsample_idx:Tensor/1/int, batch:Tensor/1/int, xyz:Tensor/2/float, window_size:float/0/float, i:int/0/int, logger:Logger/0/? · returned tuple · level recorded 2026-09-24
load_cfg_from_cfg_file in 24 papers util/config.py ran · our draft was wrong no licence file found · pointer only · 277a13798d6d6981 · report fixture: signature file:str/0/str · returned CfgNode · level recorded 2026-09-25
read_episode util/scannet_v2_fs.py ran · our draft was wrong licence not identified · pointer only · 025e0ac667ee2c93 · report fixture: signature file_name:str/0/str · returned tuple · level recorded 2026-09-24
read_ply_xyzrgb in 5 papers preprocess/collect_scannet_data.py ran · honoured contract licence not identified · pointer only · 2a7a424f68f709a9 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
room2blocks preprocess/room2blocks.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 1f157843d7098093 · report fixture: signature data:ndarray/2/float, block_size:float/0/float, stride:float/0/float, min_npts:int/0/int · returned list · level recorded 2026-09-24
room2blocks_wrapper preprocess/room2blocks.py ran · our draft was wrong licence not identified · pointer only · 02332b3ff14b4e4c · report fixture: signature room_path:str/0/str, block_size:float/0/float, stride:float/0/float, min_npts:int/0/int · returned list · level recorded 2026-09-24
evaluate_metric util/common_util.py unverified licence not identified · pointer only · a0b2c2582a9d86f7 · report
get_raw2scannet_label_map preprocess/collect_scannet_data.py unverified no licence file found · pointer only · f13268f02f8a1e65 · report
grid_sample in 18 papers model/stratified_transformer.py unverified licence not identified · pointer only · 59471dbb2f62e91f · report
load_pretrain_bakcbone util/common_util.py unverified licence not identified · pointer only · a6d5d25f5616f1a6 · report
load_pretrain_checkpoint util/common_util.py unverified licence not identified · pointer only · b4b4ff374bfbb742 · report
merge_cfg_from_list in 24 papers util/config.py unverified no licence file found · pointer only · 4efe685c6fb1ec11 · report

Tasks

Few-shot 3D Point Cloud Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASEFocus

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