SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.00592 · CVPR · 2024

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

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

arXiv · PDF · Open in the Atlas

Code that ran

10 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.00592.json · badge: /api/ran/2403.00592.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ZhaochongAn/COSeg canonical (classifier label)
classifier basis: census
10 ran · 6 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
ZhaochongAn/COSeg/util/data_util.py
pointer only (licence: NOASSERTION) · get_code("a8ff948bb3cab6fd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

collate_fn_limit_fs Ran
ran; our contract draft was wrong, not the code
ZhaochongAn/COSeg/util/data_util.py
pointer only (licence: NOASSERTION) · get_code("cba5e0e87ac98a87")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

collate_fn_limit_fs_train Ran
ran; our contract draft was wrong, not the code
ZhaochongAn/COSeg/util/data_util.py
pointer only (licence: NOASSERTION) · get_code("54d071dd22199b3d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

elu_feature_map Ran
ran, honoured the contract we drafted
ZhaochongAn/COSeg/model/common.py
pointer only (licence: NONE) · get_code("0d5505bd782b4a89")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhaochongAn/COSeg when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_indice_pairs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZhaochongAn/COSeg/model/stratified_transformer.py
pointer only (licence: NOASSERTION) · get_code("0ae5d1534c27c4af")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_cfg_from_cfg_file Ran
ran; our contract draft was wrong, not the code
ZhaochongAn/COSeg/util/config.py
pointer only (licence: NONE) · get_code("277a13798d6d6981")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhaochongAn/COSeg when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_episode Ran
ran; our contract draft was wrong, not the code
ZhaochongAn/COSeg/util/scannet_v2_fs.py
pointer only (licence: NOASSERTION) · get_code("025e0ac667ee2c93")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_ply_xyzrgb Ran
ran, honoured the contract we drafted
ZhaochongAn/COSeg/preprocess/collect_scannet_data.py
pointer only (licence: NOASSERTION) · get_code("2a7a424f68f709a9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

room2blocks Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ZhaochongAn/COSeg/preprocess/room2blocks.py
pointer only (licence: NOASSERTION) · get_code("1f157843d7098093")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

room2blocks_wrapper Ran
ran; our contract draft was wrong, not the code
ZhaochongAn/COSeg/preprocess/room2blocks.py
pointer only (licence: NOASSERTION) · get_code("02332b3ff14b4e4c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_metric Not yet run
unverified (harvested, no recorded run)
ZhaochongAn/COSeg/util/common_util.py
pointer only (licence: NOASSERTION) · get_code("a0b2c2582a9d86f7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_raw2scannet_label_map Not yet run
unverified (harvested, no recorded run)
ZhaochongAn/COSeg/preprocess/collect_scannet_data.py
pointer only (licence: NONE); the stored copy get_code serves, from yangyangyang127/seg-nn, is pointer only (licence: NONE) · get_code("f13268f02f8a1e65")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhaochongAn/COSeg when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

grid_sample Not yet run
unverified (harvested, no recorded run)
ZhaochongAn/COSeg/model/stratified_transformer.py
pointer only (licence: NOASSERTION) · get_code("59471dbb2f62e91f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_pretrain_bakcbone Not yet run
unverified (harvested, no recorded run)
ZhaochongAn/COSeg/util/common_util.py
pointer only (licence: NOASSERTION) · get_code("a6d5d25f5616f1a6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_pretrain_checkpoint Not yet run
unverified (harvested, no recorded run)
ZhaochongAn/COSeg/util/common_util.py
pointer only (licence: NOASSERTION) · get_code("b4b4ff374bfbb742")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ZhaochongAn/COSeg (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

merge_cfg_from_list Not yet run
unverified (harvested, no recorded run)
ZhaochongAn/COSeg/util/config.py
pointer only (licence: NONE) · get_code("4efe685c6fb1ec11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ZhaochongAn/COSeg when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 10 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 6 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
merge_cfg_from_list 23 other papers
16 dated earlier, 7 later
2003.13328 (2020-03)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
and 20 more not named here
load_cfg_from_cfg_file 22 other papers
15 dated earlier, 7 later
2003.13328 (2020-03)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
and 19 more not named here
elu_feature_map 14 other papers
9 dated earlier, 4 later, 1 same year, order not determinable · 2 only as an assembly brick
2104.00680 (2021-04)
LoFTR: Detector-Free Local Feature Matching with Transformers
2203.09645 (2022-03)
MatchFormer: Interleaving Attention in Transformers for Feature Matching
2203.10981 (2022-03)
MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer
and 11 more not named here
get_raw2scannet_label_map 3 other papers
2 dated earlier, 1 later
2006.12052 (2020-06)
Few-shot 3D Point Cloud Semantic Segmentation
2308.03177 (2023-08)
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
2404.04050 (2024-04)
No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
read_ply_xyzrgb 3 other papers
2 dated earlier, 1 later
2006.12052 (2020-06)
Few-shot 3D Point Cloud Semantic Segmentation
2308.03177 (2023-08)
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
2404.04050 (2024-04)
No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
collate_fn 2 other papers
2 dated earlier
2212.02011 (2022-12)
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
grid_sample 2 other papers
2 dated earlier
2203.14508 (2022-03)
Stratified Transformer for 3D Point Cloud Segmentation
room2blocks 2 other papers
2 dated earlier
2006.12052 (2020-06)
Few-shot 3D Point Cloud Semantic Segmentation
2308.03177 (2023-08)
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
room2blocks_wrapper 2 other papers
2 dated earlier
2006.12052 (2020-06)
Few-shot 3D Point Cloud Semantic Segmentation
2308.03177 (2023-08)
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
evaluate_metric 1 other paper
1 later
2410.22489 (2024-10)
Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 Multiprototypical 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 github.com/ZhaochongAn/COSeg.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.00592")
get_code_for_paper("2403.00592")
have("2403.00592")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.00592.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.00592.svg)](https://syntology.ai/paper/2403.00592)

Connect an agent — have() is free.