SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.06368 · 2019

Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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, 2 violated it and 7 have no contract verdict; 4 failures of our instrument; 4 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/1905.06368.json · badge: /api/ran/1905.06368.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
chenwydj/ultra_high_resolution_segmentation canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
FunctionStatusWhere it lives
RGB_mapping_to_class Ran
ran on a synthesized input
chenwydj/ultra_high_resolution_segmentation/dataset/deep_globe.py
code served (permissive licence) · get_code("83164b90f29b12b6")
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 2, dtype family float, shape (4, 5) 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

# The function takes a label parameter which is a numpy array with shape (height, width, 3)
# representing an RGB image where each pixel is a 3-tuple of RGB values.
# The function maps specific RGB colors to class indices.

# Create a small test label array with shape (4, 5, 3)
# Mix different RGB colors that the function recognizes
label = np.array([
    [[0, 255, 255], [255, 255, 0], [255, 0, 255], [0, 255, 0], [0, 0, 255]],
    [[255, 255, 255], [0, 0, 0], [0, 255, 255], [255, 255, 0], [255, 0, 255]],
    [[0, 255, 0], [0, 0, 255], [255, 255, 255], [0, 0, 0], [0, 255, 255]],
    [[255, 255, 0], [255, 0, 255], [0, 255, 0], [0, 0, 255], [255, 255, 255]]
], dtype=np.uint8)

ARGS = {
    "label": label
}
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 ndarray, ndim 2, dtype family float, shape (4, 5) — shape (4, 5) 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
chenwydj/ultra_high_resolution_segmentation/models/resnet_dilation.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.

find_label_map_name Ran
ran on a synthesized input
chenwydj/ultra_high_resolution_segmentation/dataset/deep_globe.py
code served (permissive licence) · get_code("88571e0bc1f87c4c")
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.

ARGS = {
    'img_filenames': 'path/to/image_sat.jpg',
    'labelExtension': '.png'
}
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
images_transform Ran
ran on a synthesized input
chenwydj/ultra_high_resolution_segmentation/helper.py
code served (permissive licence) · get_code("fee7ad2e9af58d46")
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 4, dtype family float, shape (2, 3, 4, 3) 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
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create small PIL images for testing
# Make images with distinct dimensions: 4x3 (height x width)
img_array_1 = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
img_array_2 = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

pil_img_1 = Image.fromarray(img_array_1)
pil_img_2 = Image.fromarray(img_array_2)

images_list = [pil_img_1, pil_img_2]

ARGS = {
    "images": images_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 3) — shape (2, 3, 4, 3) 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 on a synthesized input
chenwydj/ultra_high_resolution_segmentation/utils/lovasz_losses.py
code served (permissive licence) · get_code("0fc87425bc96807d")
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 float64, ndim 0, 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 numpy as np
import torch

torch.manual_seed(0)

# Build small numpy arrays for predictions and labels
# Binary classification: values should be 0 or 1
# Make them small (batch size 2, spatial dims 4x3)
preds = np.array([
    [[0, 1, 0, 1], [1, 0, 1, 0], [0, 1, 1, 0]],
    [[1, 1, 0, 0], [0, 0, 1, 1], [1, 0, 0, 1]]
], dtype=np.int32)

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

# EMPTY: value to return when union is empty
EMPTY = 1.0

# ignore: class index to ignore (None means no class is ignored)
ignore = None

# per_image: whether to compute IoU per image (True) or globally (False)
per_image = True

ARGS = {
    "preds": preds,
    "labels": labels,
    "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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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_image_file Ran
ran, violated the contract we drafted
chenwydj/ultra_high_resolution_segmentation/dataset/deep_globe.py
code served (permissive licence) · get_code("0516d5020cce56da")
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 bool, 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 torch
import numpy as np

def is_image_file(filename):
    return any((filename.endswith(extension) for extension in ['.png', '.jpg', '.jpeg']))

ARGS = {
    'filename': 'test_image.jpg'
}
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 bool, 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
lovasz_grad Ran
ran, violated the contract we drafted
chenwydj/ultra_high_resolution_segmentation/utils/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
masks_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chenwydj/ultra_high_resolution_segmentation/helper.py
code served (permissive licence) · get_code("ef246a258385aff1")
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 int, shape (2, 4, 3) 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 numpy as np
import torch

torch.manual_seed(0)

# Create a list of PIL-like mask objects or numpy arrays
# The function expects "list of PIL images" but works with array-like objects
mask1 = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)
mask2 = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)

# Ensure at least one mask has a 255 value to test the replacement logic
mask1[0, 0] = 255
mask2[1, 1] = 255

masks = [mask1, mask2]

ARGS = {
    "masks": masks,
    "numpy": False
}
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 Tensor, ndim 3, dtype family int, shape (2, 4, 3) — shape (2, 4, 3) 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
one_hot Ran
ran on a synthesized input
chenwydj/ultra_high_resolution_segmentation/utils/loss.py
code served (permissive licence) · get_code("75fbeebf4d62eccd")
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 2, dtype family float, shape (4, 4) 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)

# index: a tensor that will be viewed and scattered into
# The function calls index.size()[:1] to get batch size, then .view(view)
# So index should be 1D or have a batch dimension
index = torch.tensor([0, 2, 1, 3], dtype=torch.long)

# classes: an integer representing number of classes
classes = 4

ARGS = {
    "index": index,
    "classes": classes
}
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 2, dtype family float, shape (4, 4) — shape (4, 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
resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chenwydj/ultra_high_resolution_segmentation/helper.py
code served (permissive licence) · get_code("31b90680f5041dcc")
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 4, dtype family int; 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.

from PIL import Image
import numpy as np

# Create small PIL images for testing
img1 = Image.new('RGB', (10, 8), color='red')
img2 = Image.new('RGB', (10, 8), color='blue')

# Create a label image (grayscale for semantic segmentation-like use)
label_img1 = Image.new('L', (10, 8), color=50)
label_img2 = Image.new('L', (10, 8), color=100)

ARGS = {
    'images': [img1, img2],
    'shape': (5, 4),
    'label': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 4, dtype family int — 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
resnet101 Ran
ran on a synthesized input
chenwydj/ultra_high_resolution_segmentation/models/resnet.py
code served (permissive licence) · get_code("c7423f05f117cdcb")
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 ResNet. 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)

ARGS = {
    'pretrained': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet50 Ran
ran on a synthesized input
chenwydj/ultra_high_resolution_segmentation/models/resnet.py
code served (permissive licence) · get_code("8d58c0005a32eac6")
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 ResNet. 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)

ARGS = {
    'pretrained': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
short_hash Ran
ran; our contract draft was wrong, not the code
chenwydj/ultra_high_resolution_segmentation/models/model_store.py
code served (permissive licence) · get_code("2dcd89bf466544aa")
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

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_file Not yet run
unverified (harvested, no recorded run)
chenwydj/ultra_high_resolution_segmentation/models/model_store.py
code served (permissive licence) · get_code("5aca26e2a8b0f1a0")
How it ran

no invocation recorded.

iou Not yet run
unverified (harvested, no recorded run)
chenwydj/ultra_high_resolution_segmentation/utils/lovasz_losses.py
code served (permissive licence) · get_code("3d751ab2b52adb8f")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
chenwydj/ultra_high_resolution_segmentation/models/resnet_dilation.py
code served (permissive licence) · get_code("b170e2d6a36d1f07")
How it ran

no invocation recorded.

resnet34 Not yet run
unverified (harvested, no recorded run)
chenwydj/ultra_high_resolution_segmentation/models/resnet_dilation.py
code served (permissive licence) · get_code("27ca382809ba86cf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 13 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 13 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
119 dated earlier, 12 the same month, 555 later · 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
resnet18 89 other papers
15 dated earlier, 2 the same month, 72 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
resnet34 53 other papers
14 dated earlier, 1 the same month, 38 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 50 more not named here
lovasz_grad 40 other papers
3 dated earlier, 37 later · 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
short_hash 11 other papers
2 dated earlier, 1 the same month, 8 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 8 other papers
3 dated earlier, 5 later
1802.08797 (2018-02)
Residual Dense Network for Image Super-Resolution
1803.02735 (2018-03)
Deep Back-Projection Networks For Super-Resolution
1903.10128 (2019-03)
Recurrent Back-Projection Network for Video Super-Resolution
and 5 more not named here
get_model_file 2 other papers
2 later
2003.13328 (2020-03)
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
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
one_hot 2 other papers
2 later
1912.10917 (2019-12)
FasterSeg: Searching for Faster Real-time Semantic Segmentation
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
images_transform 1 other paper
1 later
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
masks_transform 1 other paper
1 later
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
resize 1 other paper
1 later
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
resnet101 1 other paper
1 later
2110.00970 (2021-10)
Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement
resnet50 1 other paper
1 later
2110.00970 (2021-10)
Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement

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

Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultra-high resolution image or crop it into small patches for separate processing. In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy. We propose collaborative Global-Local Networks (GLNet) to effectively preserve both global and local information in a highly memory-efficient manner. GLNet is composed of a global branch and a local branch, taking the downsampled entire image and its cropped local patches as respective inputs. For segmentation, GLNet deeply fuses feature maps from two branches, capturing both the high-resolution fine structures from zoomed-in local patches and the contextual dependency from the downsampled input. To further resolve the potential class imbalance problem between background and foreground regions, we present a coarse-to-fine variant of GLNet, also being memory-efficient. Extensive experiments and analyses have been performed on three real-world ultra-high aerial and medical image datasets (resolution up to 30 million pixels). With only one single 1080Ti GPU and less than 2GB memory used, our GLNet yields high-quality segmentation results and achieves much more competitive accuracy-memory usage trade-offs compared to state-of-the-arts.

For agents

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

get_harvested_code_for_paper("1905.06368")
get_code_for_paper("1905.06368")
have("1905.06368")

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

curl https://syntology.ai/api/ran/1905.06368.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.06368.svg)](https://syntology.ai/paper/1905.06368)

Connect an agent — have() is free.