SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.10537 · 2024

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

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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; 3 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 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/2408.10537.json · badge: /api/ran/2408.10537.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
Javion11/PointLiBR canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
bernoulli_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Javion11/PointLiBR/main/main_inv.py
code served (permissive licence) · get_code("41f42919cf5b6978")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Construct valid arguments for bernoulli_mask function
# The function expects:
# - target: tensor of class indices
# - point_num: array/list of point counts per class (determines truncation logic)
# - offset: tensor of offsets
# - ignore_index: integer indicating which index to ignore

# Choose point_num length to be 13 (triggers truncation = -6)
point_num = np.array([100, 150, 200, 120, 180, 90, 110, 160, 140, 130, 170, 105, 125], dtype=np.float32)

# Create target tensor with class indices matching point_num length
# Values should be in range [0, len(point_num)-1] or [1, len(point_num)] depending on ignore_index
target = torch.tensor([0, 1, 5, 3, 2, 4, 1, 2], dtype=torch.long)

# Create offset tensor - these are cumulative offsets for segments
offset = torch.tensor([2, 5, 8], dtype=torch.long)

# Set ignore_index to 0 (triggers special handling in the function)
ignore_index = 0

ARGS = {
    "target": target,
    "point_num": point_num,
    "offset": offset,
    "ignore_index": ignore_index
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
collate_fn Ran
ran; our contract draft was wrong, not the code
Javion11/PointLiBR/openpoints/dataset/build.py
code served (permissive licence) · get_code("f7bd8f9551547241")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from collections.abc import Mapping, Sequence

torch.manual_seed(0)

# Test case 1: batch of Tensors
batch_tensors = [torch.randn(2, 4), torch.randn(2, 4)]

# Test case 2: batch of strings
batch_strings = ["sample1", "sample2"]

# Test case 3: batch of sequences (lists) with coords and offsets
batch_sequences = [
    [torch.randn(3, 4), torch.tensor([3])],
    [torch.randn(5, 4), torch.tensor([5])]
]

# Test case 4: batch of dicts with coords and offset keys
batch_dicts = [
    {
        "coord": torch.randn(2, 4),
        "offset": torch.tensor([2]),
        "feature": torch.randn(2, 8)
    },
    {
        "coord": torch.randn(3, 4),
        "offset": torch.tensor([3]),
        "feature": torch.randn(3, 8)
    }
]

# Test case 5: batch of scalars/simple data
batch_scalars = [1, 2, 3]

# Use the dict batch as the primary test case
ARGS = {
    "batch": batch_dicts
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fnv_hash_vec Ran
ran, honoured the contract we drafted
Javion11/PointLiBR/openpoints/dataset/data_util.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("0086c892bd1df796")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (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.

gen_sample Ran
ran; our contract draft was wrong, not the code
Javion11/PointLiBR/main/main_spg.py
code served (permissive licence) · get_code("1176105bd90f0374")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Analyze the function:
# - numbers: int (used in .repeat())
# - mu: tensor with shape (class_num, prior_feas_dim), gets unsqueezed and repeated
# - std: float with default 0.05

numbers = 2
class_num = 3
prior_feas_dim = 4
mu = torch.randn(class_num, prior_feas_dim)
std = 0.05

ARGS = {
    "numbers": numbers,
    "mu": mu,
    "std": std,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Javion11/PointLiBR/openpoints/loss/lovasz_losses.py
code served (permissive licence) · get_code("d94639b28b2134ff")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# Construct valid arguments for the iou function
# preds: prediction array/tensor with class indices
# labels: ground truth array/tensor with class indices
# C: number of classes
# EMPTY: value to return for empty unions (default 1.0)
# ignore: class index to ignore (default None)
# per_image: whether to compute per-image IoU (default False)

# Create small prediction and label arrays
# Using shape (2, 4) - batch of 2, spatial dimension of 4
preds = np.array([[0, 1, 2, 3],
                   [1, 2, 0, 1]], dtype=np.int64)

labels = np.array([[0, 1, 1, 3],
                    [1, 2, 2, 1]], dtype=np.int64)

# Number of classes
C = 4

# EMPTY value for classes with no union
EMPTY = 1.0

# Class to ignore during computation
ignore = None

# Whether to compute per-image IoU
per_image = False

ARGS = {
    "preds": preds,
    "labels": labels,
    "C": C,
    "EMPTY": EMPTY,
    "ignore": ignore,
    "per_image": per_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
iou_binary Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Javion11/PointLiBR/openpoints/loss/lovasz_losses.py
code served (permissive licence) · get_code("1211530cd527bd0b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

def isnan(x):
    return x != x

def mean(l, ignore_nan=False, empty=0):
    """
    nanmean compatible with generators.
    """
    l = iter(l)
    if ignore_nan:
        from itertools import filterfalse
        l = filterfalse(isnan, l)
    try:
        n = 1
        acc = next(l)
    except StopIteration:
        if empty == 'raise':
            raise ValueError('Empty mean')
        return empty
    for n, v in enumerate(l, 2):
        acc += v
    if n == 1:
        return acc
    return acc / n

def iou_binary(preds, labels, EMPTY=1.0, ignore=None, per_image=True):
    """
    IoU for foreground class
    binary: 1 foreground, 0 background
    """
    if not per_image:
        preds, labels = ((preds,), (labels,))
    ious = []
    for pred, label in zip(preds, labels):
        intersection = ((label == 1) & (pred == 1)).sum()
        union = ((label == 1) | (pred == 1) & (label != ignore)).sum()
        if not union:
            iou = EMPTY
        else:
            iou = float(intersection) / float(union)
        ious.append(iou)
    iou = mean(ious)
    return 100 * iou

# Setup code
np.random.seed(0)

# Create small prediction and label arrays for binary segmentation
# Shape: (height=4, width=3) for two images
preds_img1 = np.array([[0, 1, 1],
                       [1, 1, 0],
                       [0, 1, 1],
                       [1, 0, 0]], dtype=np.int32)

labels_img1 = np.array([[0, 1, 0],
                        [1, 1, 1],
                        [0, 1, 0],
                        [1, 0, 1]], dtype=np.int32)

preds_img2 = np.array([[1, 1, 0],
                       [0, 1, 1],
                       [1, 1, 0],
                       [0, 0, 1]], dtype=np.int32)

labels_img2 = np.array([[1, 0, 0],
                        [0, 1, 1],
                        [1, 0, 0],
                        [0, 1, 1]], dtype=np.int32)

# Arguments for iou_binary function
ARGS = {
    'preds': np.array([preds_img1, preds_img2]),
    'labels': np.array([labels_img1, labels_img2]),
    'EMPTY': 1.0,
    'ignore': 0,
    'per_image': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_model Ran
ran, violated the contract we drafted
Javion11/PointLiBR/openpoints/models/registry.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("cd2a47ded9dd84cf")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (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.

list_models Ran
ran, honoured the contract we drafted
Javion11/PointLiBR/openpoints/models/registry.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("d14a6ca5ff9d530e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (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.

lovasz_grad Ran
ran, violated the contract we drafted
Javion11/PointLiBR/openpoints/loss/lovasz_losses.py
code served (permissive licence) · get_code("e85b5d21dc5b8382")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# gt_sorted should be a 1D tensor of binary/boolean values
# representing ground truth sorted by some error metric
# The function expects a tensor with sum(), float(), cumsum() methods
gt_sorted = torch.tensor([0, 0, 1, 1], dtype=torch.long)

ARGS = {
    "gt_sorted": gt_sorted
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mask_target Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Javion11/PointLiBR/main/main_inv.py
code served (permissive licence) · get_code("ebfa7541d28ada0e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Analyze the function to understand what each parameter needs:
# - target: tensor that supports != comparison and indexing with boolean mask
# - offset: tensor with .size(0) method and indexing, should be 1D
# - pos: tensor that supports boolean indexing
# - ignore_index: integer or value that can be compared with tensor elements

# Create small tensors with distinct sizes for clarity
target = torch.tensor([0, 1, 2, 0, 3, 1], dtype=torch.long)  # 6 elements
offset = torch.tensor([2, 4, 6], dtype=torch.long)  # 3 elements
pos = torch.arange(6 * 4).reshape(6, 4)  # 6x4 tensor to match target length
ignore_index = 0

ARGS = {
    "target": target,
    "offset": offset,
    "pos": pos,
    "ignore_index": ignore_index
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
point_collate_fn Ran
ran; our contract draft was wrong, not the code
Javion11/PointLiBR/openpoints/dataset/build.py
code served (permissive licence) · get_code("b7dd33a246b1c8b6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import random
from collections.abc import Mapping, Sequence

torch.manual_seed(0)

# Test case 1: batch of Mapping (dict) objects with 'offset' key
batch_mapping = [
    {
        'coord': torch.randn(3, 4),
        'offset': torch.tensor([3]),
        'label': torch.tensor([0])
    },
    {
        'coord': torch.randn(2, 4),
        'offset': torch.tensor([2]),
        'label': torch.tensor([1])
    }
]

ARGS = {
    'batch': batch_mapping,
    'mix_prob': 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ravel_hash_vec Ran
ran, honoured the contract we drafted
Javion11/PointLiBR/openpoints/dataset/data_util.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("afdc8ad15d9098b8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (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.

register_model Ran
ran; our contract draft was wrong, not the code
Javion11/PointLiBR/openpoints/models/registry.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("e13039fb1c347452")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (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.

download_url Not yet run
unverified (harvested, no recorded run)
Javion11/PointLiBR/openpoints/dataset/data_util.py
pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("556e417290a6e1fd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (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.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 10 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 2 the same month, 10 later) and 4 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
lovasz_grad 40 other papers
31 dated earlier, 7 later, 2 same year, order not determinable · 1 only as an assembly brick
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
and 37 more not named here
iou 24 other papers
19 dated earlier, 4 later, 1 same year, order not determinable
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
and 21 more not named here
iou_binary 24 other papers
19 dated earlier, 4 later, 1 same year, order not determinable
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
and 21 more not named here
is_model 22 other papers
21 dated earlier, 1 later
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 19 more not named here
fnv_hash_vec 12 other papers
8 dated earlier, 1 the same month, 3 later
2211.15654 (2022-11)
OpenScene: 3D Scene Understanding with Open Vocabularies
2212.02011 (2022-12)
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
and 9 more not named here
list_models 12 other papers
11 dated earlier, 1 later
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 9 more not named here
ravel_hash_vec 12 other papers
9 dated earlier, 1 the same month, 2 later
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2211.15654 (2022-11)
OpenScene: 3D Scene Understanding with Open Vocabularies
2212.02011 (2022-12)
PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
and 9 more not named here
register_model 11 other papers
10 dated earlier, 1 later
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 8 more not named here
download_url 6 other papers
5 dated earlier, 1 later
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2303.16450 (2023-03)
Self-positioning Point-based Transformer for Point Cloud Understanding
and 3 more not named here
collate_fn 1 other paper
1 later
2411.07184 (2024-11)
SAMPart3D: Segment Any Part in 3D Objects

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

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}.

For agents

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

get_harvested_code_for_paper("2408.10537")
get_code_for_paper("2408.10537")
have("2408.10537")

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

curl https://syntology.ai/api/ran/2408.10537.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.10537.svg)](https://syntology.ai/paper/2408.10537)

Connect an agent — have() is free.