SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.07335 · CVPR · 2022

A Keypoint-based Global Association Network for Lane Detection

Fei Wang, Chen Qian, Tianzhu Zhang, Yinchao Ma, Shaofei Huang, Tianrui Hui, Jinsheng Wang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 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/2204.07335.json · badge: /api/ran/2204.07335.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
wolfwjs/ganet canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
zkyntu/UnLanedet community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
CtnetHead Ran
ran on a synthesized input · constructed an object; no result was computed
zkyntu/UnLanedet/unlanedet/model/GANet/head.py
code served (permissive licence) · get_code("fe6679885d8666ee")
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 an instance of its own class, CtnetHead: the run constructed the object and did not call it, so no result was computed. 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)

# Define heads_dict - the key parameter for CtnetHead
# It expects a dict where each key is a head name, and value is a dict with 'out_channels' and 'num_conv'
heads_dict = {
    'hm': {
        'out_channels': 8,
        'num_conv': 2
    },
    'wh': {
        'out_channels': 2,
        'num_conv': 3
    },
    'reg': {
        'out_channels': 2,
        'num_conv': 2
    }
}

ARGS = {
    'in_channels': 4,
    'heads_dict': heads_dict,
    'final_kernel': 1,
    'init_bias': -2.19,
    'use_bias': False
}
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 CtnetHead — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CtnetHead 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
GANetHead Ran
ran on a synthesized input · constructed an object; no result was computed
zkyntu/UnLanedet/unlanedet/model/GANet/head.py
code served (permissive licence) · get_code("d04d955eb6f89f54")
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 an instance of its own class, GANetHead: the run constructed the object and did not call it, so no result was computed. 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
import numpy as np
from scipy.interpolate import InterpolatedUnivariateSpline

torch.manual_seed(0)

# Define minimal loss functions as stand-in classes
class DummyLoss(nn.Module):
    def forward(self, *args, **kwargs):
        return torch.tensor(0.0)

# Define minimal config class
class Config:
    def __init__(self):
        self.sample_y = [100, 200, 300, 400]
        self.ori_img_w = 640
        self.ori_img_h = 480

# Define minimal test_cfg
class TestConfig:
    def __init__(self):
        self.max_lanes = 4
        self.conf_threshold = 0.5

ARGS = {
    'in_channels': 64,
    'num_classes': 1,
    'hm_idx': 0,
    'loss_heatmap': DummyLoss(),
    'loss_kp_offset': DummyLoss(),
    'loss_sp_offset': DummyLoss(),
    'loss_aux': DummyLoss(),
    'test_cfg': TestConfig(),
    'cfg': Config(),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GANetHead — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GANetHead 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
Lane Ran
ran on a synthesized input · constructed an object; no result was computed
zkyntu/UnLanedet/unlanedet/model/GANet/head.py
code served (permissive licence) · get_code("79f8d381e9a2dbc1")
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 an instance of its own class, Lane: the run constructed the object and did not call it, so no result was computed. 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 numpy as np
from scipy.interpolate import InterpolatedUnivariateSpline

# Create valid points for Lane initialization
# Points should be 2D array with shape (N, 2) where columns are [x, y]
points = np.array([
    [0.1, 0.2],
    [0.3, 0.4],
    [0.5, 0.6],
    [0.7, 0.8],
    [0.9, 1.0]
], dtype=np.float32)

# Create metadata dict
metadata = {
    "lane_id": 1,
    "confidence": 0.95
}

ARGS = {
    "points": points,
    "invalid_value": -2.0,
    "metadata": metadata
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Lane — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Lane 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
compute_locations Ran
ran on a synthesized input
wolfwjs/ganet/mmdet/models/dense_heads/ganet_head.py
code served (permissive licence) · get_code("f06980dfe43b7c39")
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

torch.manual_seed(0)

# The function expects:
# - shape: a sequence/tensor with at least a last dimension (shape[-1] is accessed)
#          and indexable by [0] and [1] for repeat operation
# - device: a torch device object

shape = (2, 3, 4)  # (batch_size, height, width) - distinct sizes for different dimensions
device = torch.device('cpu')

ARGS = {
    'shape': shape,
    'device': device
}
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
make_coordmat Ran
ran on a synthesized input
wolfwjs/ganet/mmdet/models/dense_heads/ganet_head.py
code served (permissive licence) · get_code("b8e738d2a502bad4")
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, 80, 200) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

ARGS = {
    'shape': (1, 80, 200),
    'device': torch.device('cpu')
}
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, 80, 200) — shape (2, 80, 200) 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
make_mask Ran
ran on a synthesized input
wolfwjs/ganet/mmdet/models/dense_heads/ganet_head.py
code served (permissive licence) · get_code("f58a2eec42e3f15f")
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, 5, 7) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

ARGS = {
    "shape": (2, 5, 7),
    "device": torch.device('cpu')
}
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, 5, 7) — shape (2, 5, 7) 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
kaiming_init Not yet run
unverified (harvested, no recorded run)
zkyntu/UnLanedet/unlanedet/model/GANet/head.py
code served (permissive licence) · get_code("94b6a7396eb44132")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 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
kaiming_init
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2104.06403 (2021-04)
Lite-HRNet: A Lightweight High-Resolution Network

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

Lane detection is a challenging task that requires predicting complex topology shapes of lane lines and distinguishing different types of lanes simultaneously. Earlier works follow a top-down roadmap to regress predefined anchors into various shapes of lane lines, which lacks enough flexibility to fit complex shapes of lanes due to the fixed anchor shapes. Lately, some works propose to formulate lane detection as a keypoint estimation problem to describe the shapes of lane lines more flexibly and gradually group adjacent keypoints belonging to the same lane line in a pointby-point manner, which is inefficient and time-consuming during postprocessing. In this paper, we propose a Global Association Network (GANet) to formulate the lane detection problem from a new perspective, where each keypoint is directly regressed to the starting point of the lane line instead of point-by-point extension. Concretely, the association of keypoints to their belonged lane line is conducted by predicting their offsets to the corresponding starting points of lanes globally without dependence on each other, which could be done in parallel to greatly improve efficiency. In addition, we further propose a Lane-aware Feature Aggregator (LFA), which adaptively captures the local correlations between adjacent keypoints to supplement local information to the global association. Extensive experiments on two popular lane detection benchmarks show that our method outperforms previous methods with F1 score of 79.63% on CULane and 97.71% on Tusimple dataset with high FPS.

For agents

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

get_harvested_code_for_paper("2204.07335")
get_code_for_paper("2204.07335")
have("2204.07335")

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

curl https://syntology.ai/api/ran/2204.07335.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.07335.svg)](https://syntology.ai/paper/2204.07335)

Connect an agent — have() is free.