SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13328 · 2020

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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; 0 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 4 failures of our instrument; 4 no recorded run), measured 2026-11-21; 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/2003.13328.json · badge: /api/ran/2003.13328.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
Andrew-Qibin/SPNet canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
Andrew-Qibin/SPNet/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, and GitHub detected no licence in that repository 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_city_pairs Ran
ran on a synthesized input
Andrew-Qibin/SPNet/util/cityscapes.py
code served (permissive licence) · get_code("ccb24f9418500942")
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, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile

# Create a temporary directory structure to mimic Cityscapes dataset
temp_dir = tempfile.mkdtemp()

# Create the directory structure for train split
train_img_dir = os.path.join(temp_dir, 'leftImg8bit', 'train', 'city1')
train_mask_dir = os.path.join(temp_dir, 'gtFine', 'train', 'city1')
os.makedirs(train_img_dir, exist_ok=True)
os.makedirs(train_mask_dir, exist_ok=True)

# Create dummy image and mask files for train
train_img_file = os.path.join(train_img_dir, 'sample_leftImg8bit.png')
train_mask_file = os.path.join(train_mask_dir, 'sample_gtFine_labelIds.png')
open(train_img_file, 'a').close()
open(train_mask_file, 'a').close()

# Create the directory structure for val split
val_img_dir = os.path.join(temp_dir, 'leftImg8bit', 'val', 'city2')
val_mask_dir = os.path.join(temp_dir, 'gtFine', 'val', 'city2')
os.makedirs(val_img_dir, exist_ok=True)
os.makedirs(val_mask_dir, exist_ok=True)

# Create dummy image and mask files for val
val_img_file = os.path.join(val_img_dir, 'sample_leftImg8bit.png')
val_mask_file = os.path.join(val_mask_dir, 'sample_gtFine_labelIds.png')
open(val_img_file, 'a').close()
open(val_mask_file, 'a').close()

# Create the directory structure for test split
test_img_dir = os.path.join(temp_dir, 'leftImg8bit', 'test', 'city3')
test_mask_dir = os.path.join(temp_dir, 'gtFine', 'test', 'city3')
os.makedirs(test_img_dir, exist_ok=True)
os.makedirs(test_mask_dir, exist_ok=True)

# Create dummy image and mask files for test
test_img_file = os.path.join(test_img_dir, 'sample_leftImg8bit.png')
test_mask_file = os.path.join(test_mask_dir, 'sample_gtFine_labelIds.png')
open(test_img_file, 'a').close()
open(test_mask_file, 'a').close()

ARGS = {
    'folder': temp_dir,
    'split': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_model_file Ran
ran; our contract draft was wrong, not the code
Andrew-Qibin/SPNet/models/model_store.py
code served (permissive licence) · get_code("c73140f517c549d4")
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 str. 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 os
import tempfile
import shutil

# Mock the check_sha1 and download functions that are called by get_model_file
def check_sha1(file_path, sha1_hash):
    """Mock function that always returns True to avoid actual hash checking"""
    return True

def download(url, path, overwrite=True):
    """Mock function that creates a dummy zip file"""
    import zipfile
    # Create a dummy .pth file
    pth_content = b"dummy model weights"
    os.makedirs(os.path.dirname(path), exist_ok=True)
    
    # Create a zip file with the expected model file inside
    with zipfile.ZipFile(path, 'w') as zf:
        # Extract the expected file name from the url/path
        base_name = os.path.basename(path).replace('.zip', '.pth')
        zf.writestr(base_name, pth_content)

# Inject these mocks into the module namespace
import sys
current_module = sys.modules[__name__]
current_module.check_sha1 = check_sha1
current_module.download = download

# Create a temporary directory for the test
temp_root = tempfile.mkdtemp()

ARGS = {
    'name': 'resnet50',
    'root': temp_root
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
is_image_file Ran
ran, violated the contract we drafted
Andrew-Qibin/SPNet/util/dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from sam1224/aenet, is pointer only (licence: NOASSERTION) · get_code("0684a938c70bf564")
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 sam1224/aenet, 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.

load_cfg_from_cfg_file Ran
ran; our contract draft was wrong, not the code
Andrew-Qibin/SPNet/util/config.py
code served (permissive licence) · get_code("277a13798d6d6981")
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 CfgNode. 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 tempfile
import os
import yaml

# Create a temporary YAML file for testing
temp_dir = tempfile.mkdtemp()
yaml_file = os.path.join(temp_dir, "config.yaml")

# Create a valid YAML config file with the expected structure
config_data = {
    "model": {
        "name": "test_model",
        "layers": 3,
        "hidden_dim": 64
    },
    "training": {
        "learning_rate": 0.001,
        "batch_size": 32,
        "epochs": 10
    },
    "data": {
        "dataset": "cifar10",
        "split": 0.8
    }
}

with open(yaml_file, 'w') as f:
    yaml.dump(config_data, f)

ARGS = {
    "file": yaml_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
make_dataset Ran
ran on a synthesized input
Andrew-Qibin/SPNet/util/dataset.py
code served (permissive licence) · get_code("eae0231645a2f4a4")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile

# Create temporary directory and files for the dataset
temp_dir = tempfile.mkdtemp()
data_root = temp_dir

# Create a temporary data list file for 'train' split
train_list_path = os.path.join(temp_dir, 'train_list.txt')
with open(train_list_path, 'w') as f:
    f.write('image1.png label1.png\n')
    f.write('image2.png label2.png\n')

# Create dummy image and label files
for i in range(1, 3):
    img_path = os.path.join(data_root, f'image{i}.png')
    label_path = os.path.join(data_root, f'label{i}.png')
    open(img_path, 'w').close()
    open(label_path, 'w').close()

# Create a temporary data list file for 'test' split
test_list_path = os.path.join(temp_dir, 'test_list.txt')
with open(test_list_path, 'w') as f:
    f.write('image1.png\n')
    f.write('image2.png\n')

ARGS = {
    'split': 'train',
    'data_root': data_root,
    'data_list': train_list_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
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
short_hash Ran
ran; our contract draft was wrong, not the code
Andrew-Qibin/SPNet/models/model_store.py
code served (permissive licence) · get_code("cbac586a86ff7adc")
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 str. 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

_model_sha1 = {name: checksum for checksum, name in [('25c4b50959ef024fcc050213a06b614899f94b3d', 'resnet50'), ('2a57e44de9c853fa015b172309a1ee7e2d0e4e2a', 'resnet101'), ('0d43d698c66aceaa2bc0309f55efdd7ff4b143af', 'resnet152'), ('da4785cfc837bf00ef95b52fb218feefe703011f', 'wideresnet38'), ('b41562160173ee2e979b795c551d3c7143b1e5b5', 'wideresnet50'), ('1225f149519c7a0113c43a056153c1bb15468ac0', 'deepten_resnet50_minc'), ('662e979de25a389f11c65e9f1df7e06c2c356381', 'fcn_resnet50_ade'), ('eeed8e582f0fdccdba8579e7490570adc6d85c7c', 'fcn_resnet50_pcontext'), ('54f70c772505064e30efd1ddd3a14e1759faa363', 'psp_resnet50_ade'), ('075195c5237b778c718fd73ceddfa1376c18dfd0', 'deeplab_resnet50_ade'), ('5ee47ee28b480cc781a195d13b5806d5bbc616bf', 'encnet_resnet101_coco'), ('4de91d5922d4d3264f678b663f874da72e82db00', 'encnet_resnet50_pcontext'), ('9f27ea13d514d7010e59988341bcbd4140fcc33d', 'encnet_resnet101_pcontext'), ('07ac287cd77e53ea583f37454e17d30ce1509a4a', 'encnet_resnet50_ade'), ('3f54fa3b67bac7619cd9b3673f5c8227cf8f4718', 'encnet_resnet101_ade')]}

def short_hash(name):
    if name not in _model_sha1:
        raise ValueError('Pretrained model for {name} is not available.'.format(name=name))
    return _model_sha1[name][:8]

ARGS = {
    'name': 'resnet50'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_model Not yet run
unverified (harvested, no recorded run)
Andrew-Qibin/SPNet/models/model_zoo.py
code served (permissive licence) · get_code("aa3f068596fc2ec7")
How it ran

no invocation recorded.

merge_cfg_from_list Not yet run
unverified (harvested, no recorded run)
Andrew-Qibin/SPNet/util/config.py
pointer only (licence: MIT); the stored copy get_code serves, from sam1224/aenet, is pointer only (licence: NOASSERTION) · get_code("b925dc5fd8492c34")
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 sam1224/aenet, 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.

resnet101 Not yet run
unverified (harvested, no recorded run)
Andrew-Qibin/SPNet/models/resnet.py
code served (permissive licence) · get_code("3679a69b2193a551")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
Andrew-Qibin/SPNet/models/resnet.py
code served (permissive licence) · get_code("029fabb30ec8ea8f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 6 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
conv3x3 686 other papers
197 dated earlier, 17 the same month, 471 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
merge_cfg_from_list 23 other papers
23 later
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
and 20 more not named here
load_cfg_from_cfg_file 22 other papers
22 later
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
and 19 more not named here
short_hash 11 other papers
5 dated earlier, 2 the same month, 4 later
1803.08904 (2018-03)
Context Encoding for Semantic Segmentation
1809.02983 (2018-09)
Dual Attention Network for Scene Segmentation
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
and 8 more not named here
is_image_file 5 other papers
5 later
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
2203.07615 (2022-03)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
2210.06780 (2022-10)
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
and 2 more not named here
get_city_pairs 2 other papers
2 dated earlier
1803.08904 (2018-03)
Context Encoding for Semantic Segmentation
1809.02983 (2018-09)
Dual Attention Network for Scene Segmentation
get_model_file 2 other papers
1 dated earlier, 1 later
1905.06368 (2019-05)
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
Li_From_Contexts_to_Locality_Ultra-High_Resolution_Image_Segmentation_via_Locality-Aware_ICCV_2021_paper (2021 (year only))
From Contexts to Locality: Ultra-high Resolution Image Segmentation via Locality-aware Contextual Correlation

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond conventional spatial pooling that usually has a regular shape of NxN, we rethink the formulation of spatial pooling by introducing a new pooling strategy, called strip pooling, which considers a long but narrow kernel, i.e., 1xN or Nx1. Based on strip pooling, we further investigate spatial pooling architecture design by 1) introducing a new strip pooling module that enables backbone networks to efficiently model long-range dependencies, 2) presenting a novel building block with diverse spatial pooling as a core, and 3) systematically comparing the performance of the proposed strip pooling and conventional spatial pooling techniques. Both novel pooling-based designs are lightweight and can serve as an efficient plug-and-play module in existing scene parsing networks. Extensive experiments on popular benchmarks (e.g., ADE20K and Cityscapes) demonstrate that our simple approach establishes new state-of-the-art results. Code is made available at https://github.com/Andrew-Qibin/SPNet.

For agents

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

get_harvested_code_for_paper("2003.13328")
get_code_for_paper("2003.13328")
have("2003.13328")

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

curl https://syntology.ai/api/ran/2003.13328.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.13328.svg)](https://syntology.ai/paper/2003.13328)

Connect an agent — have() is free.