SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.01226 · CVPR · 2021

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

Jingdong Wang, Yuhui Yuan, Xiaokang Chen, Gang Zeng

arXiv · PDF · Open in the Atlas

Code that ran

27 of 39 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 4 violated it and 12 have no contract verdict; 9 failures of our instrument; 12 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/2106.01226.json · badge: /api/ran/2106.01226.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
charlesCXK/TorchSemiSeg canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
harshm121/m3l community
Papers with Code archive
19 ran · 9 no recorded run
yhuang1997/3D-CPS community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
BaseLR Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("43976b9c757e2931")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

DepthTrainPre Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("7376c94156eef50e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

DepthValPre Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("0525b2902320166f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

RGBDTrainPre Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("ee5ad1935ccce67d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

RGBDValPre Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("fa35dd778049b33e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

RGBTrainPre Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("aec285de0ab732b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

RGBValPre Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("8db3a8167f167a90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

WarmUpPolyLR Ran
ran on a synthesized input · constructed an object; no result was computed
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("f1fa2c7b643051a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

_sliding_collate_fn Ran
ran; our contract draft was wrong, not the code
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("de4ac68ef98bebc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

bce2d Ran
ran on a synthesized input
charlesCXK/TorchSemiSeg/furnace/seg_opr/loss_opr.py
code served (permissive licence) · get_code("3bcf2f021ec54810")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create input tensor: shape (b, c, h, w) = (2, 3, 4, 5)
# This is logits for binary cross entropy with logits
input_tensor = torch.randn(2, 3, 4, 5, dtype=torch.float32)

# Create target tensor: shape (b, c, h, w) = (2, 3, 4, 5)
# Values should be 0 (negative), 1 (positive), or >1 (ignore)
target_tensor = torch.randint(0, 2, (2, 3, 4, 5), dtype=torch.float32)

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
}
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 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
compute_metrics Ran
ran, honoured the contract we drafted
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("e74fcb04fd589c71")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

compute_score Ran
ran; our contract draft was wrong, not the code
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("203e73feddb57884")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
charlesCXK/TorchSemiSeg/furnace/base_model/hrnet.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.

convert_CT_seg Ran
ran, violated the contract we drafted
yhuang1997/3D-CPS/nnunet/dataset_conversion/Task037_038_Chaos_Challenge.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from boqian333/e2enet-medical, is pointer only (licence: NONE) · get_code("c6cd5ad91c3a2851")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from boqian333/e2enet-medical, 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.

convert_MR_seg Ran
ran, honoured the contract we drafted
yhuang1997/3D-CPS/nnunet/dataset_conversion/Task037_038_Chaos_Challenge.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from boqian333/e2enet-medical, is pointer only (licence: NONE) · get_code("74dcea3d4dcc90a5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from boqian333/e2enet-medical, 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.

convert_labels_back_to_BraTS Ran
ran, violated the contract we drafted
yhuang1997/3D-CPS/nnunet/dataset_conversion/Task032_BraTS_2018.py
code served (permissive licence) · get_code("a2c8b38ba9393780")
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 3, dtype family int, 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 numpy as np

# Create a small segmentation array for testing
# The array has values 0, 1, 2, 3 which will be converted
seg = np.array([
    [[0, 1, 2, 3],
     [1, 0, 3, 2],
     [2, 3, 0, 1]],
    [[3, 2, 1, 0],
     [0, 1, 2, 3],
     [1, 2, 3, 0]]
], dtype=np.uint8)

ARGS = {
    "seg": seg
}
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 3, dtype family int, 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
hist_info Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("9e85fa995eda358a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

log_det_by_cholesky Ran
ran on a synthesized input
charlesCXK/TorchSemiSeg/furnace/seg_opr/rmi_loss.py
code served (permissive licence) · get_code("c48d876b9a3ae27a")
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 (2, 3) 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)

# Create a positive definite matrix
# Shape [N, C, D, D] where N=2, C=3, D=4
N, C, D = 2, 3, 4

# Generate random matrices and make them positive definite
# by computing A^T @ A for each matrix
random_matrices = torch.randn(N, C, D, D)
matrix = torch.bmm(
    random_matrices.reshape(N*C, D, D).transpose(-2, -1),
    random_matrices.reshape(N*C, D, D)
).reshape(N, C, D, D)

ARGS = {
    "matrix": matrix
}
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 (2, 3) — shape (2, 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
map_get_pairs Ran
ran on a synthesized input
charlesCXK/TorchSemiSeg/furnace/seg_opr/rmi_loss.py
code served (permissive licence) · get_code("97f5e3b69f2c69ea")
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 5, dtype family float, shape (2, 4, 18, 5, 3) 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)

# Create small 4D tensors with shape [N, C, H, W]
# N=2 (batch), C=4 (channels), H=7 (height), W=5 (width)
labels_4D = torch.randint(0, 2, (2, 4, 7, 5), dtype=torch.long)
probs_4D = torch.rand(2, 4, 7, 5, dtype=torch.float32)

ARGS = {
    "labels_4D": labels_4D,
    "probs_4D": probs_4D,
    "radius": 3,
    "is_combine": True
}
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 5, dtype family float, shape (2, 4, 18, 5, 3) — shape (2, 4, 18, 5, 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
map_get_pairs_region Ran
ran on a synthesized input
charlesCXK/TorchSemiSeg/furnace/seg_opr/rmi_loss.py
code served (permissive licence) · get_code("99b42d109e83351a")
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 6, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small 4D tensors for labels and probabilities
# Shape: [N, C, H, W] = [2, 4, 8, 8]
# N=2 (batch), C=4 (channels/classes), H=8, W=8 (spatial dimensions)
labels_4D = torch.randint(0, 2, (2, 4, 8, 8), dtype=torch.float32)
probs_4D = torch.rand(2, 4, 8, 8, dtype=torch.float32)

ARGS = {
    "labels_4D": labels_4D,
    "probs_4D": probs_4D,
    "radius": 3,
    "is_combine": 0,
    "num_classeses": 4
}
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, ndim 6, 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
normalize Ran
ran, violated the contract we drafted
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("17cb5b0dfa01b491")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

normalizedepth Ran
ran, violated the contract we drafted
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("815e160273134736")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

random_mirror Ran
ran; our contract draft was wrong, not the code
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("356686ea476b6ce4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

random_scale Ran
ran; our contract draft was wrong, not the code
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("ee31a169e3121523")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

resizedepth Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("cdc6961513bc7352")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

resizegt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("f385fb867a898c19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

resizergb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("b7dfd9cbf7eedacb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l 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.

AbstractFramework Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("7c76a16e37d76d1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

CPSFramework Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("fbf76f33c68cc257")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate_random_crop_pos Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("4f9f5a818fe83273")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_2dshape Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("fabc41fbf8341410")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_preprocessors Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("891adce76c9b1ef4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_seg_hrnet_w18s Not yet run
unverified (harvested, no recorded run)
charlesCXK/TorchSemiSeg/furnace/base_model/hrnet.py
pointer only (licence: MIT); the stored copy get_code serves, from TY-Shi/FreeCOS, is pointer only (licence: NONE) · get_code("636b23389eba27a1")
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 TY-Shi/FreeCOS, 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. No invocation recorded.

get_seg_hrnet_w48 Not yet run
unverified (harvested, no recorded run)
charlesCXK/TorchSemiSeg/furnace/base_model/hrnet.py
pointer only (licence: MIT); the stored copy get_code serves, from TY-Shi/FreeCOS, is pointer only (licence: NONE) · get_code("835ca2564a9653a6")
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 TY-Shi/FreeCOS, 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. No invocation recorded.

get_train_loader Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("74ffeedbf2acc130")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_val_loader Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("7dbd86b9ed974d1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_png_stack Not yet run
unverified (harvested, no recorded run)
yhuang1997/3D-CPS/nnunet/dataset_conversion/Task037_038_Chaos_Challenge.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from boqian333/e2enet-medical, is pointer only (licence: NONE) · get_code("29176ca87f23c2d7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from boqian333/e2enet-medical, 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. No invocation recorded.

pad_image_to_shape Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("17881896b84793bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

random_crop_pad_to_shape Not yet run
unverified (harvested, no recorded run)
harshm121/m3l/src/semi_supervised/cps.py
pointer only (licence: NONE) · get_code("35bbfab3ce7415bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harshm121/m3l when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 39 samples lifted from this paper's linked repositories, 39 carry a function identity and 0 do not. Of the 39 distinct functions with an identity, 12 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 8 later) and 27 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
312 dated earlier, 12 the same month, 356 later, 6 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
convert_labels_back_to_BraTS 9 other papers
9 later
2205.04846 (2022-05)
MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation
2303.09975 (2023-03)
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
2312.04727 (2023-12)
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
and 6 more not named here
convert_CT_seg 3 other papers
3 later
2205.04846 (2022-05)
MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation
2303.09975 (2023-03)
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
2312.04727 (2023-12)
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
convert_MR_seg 3 other papers
3 later
2205.04846 (2022-05)
MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation
2303.09975 (2023-03)
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
2312.04727 (2023-12)
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
hist_info
brick of this paper's assembly: helper
3 other papers
3 dated earlier
1808.00897 (2018-08)
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
1909.12513 (2019-09)
Learnable Tree Filter for Structure-preserving Feature Transform
2007.09365 (2020-07)
Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing
load_png_stack 3 other papers
3 later
2205.04846 (2022-05)
MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation
2303.09975 (2023-03)
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation
2312.04727 (2023-12)
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
normalize
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later
2007.09365 (2020-07)
Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing
2208.10169 (2022-08)
Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation
2411.03829 (2024-11)
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
log_det_by_cholesky 2 other papers
2 dated earlier
1910.12037 (2019-10)
Region Mutual Information Loss for Semantic Segmentation
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
map_get_pairs 2 other papers
2 dated earlier
1910.12037 (2019-10)
Region Mutual Information Loss for Semantic Segmentation
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
map_get_pairs_region 2 other papers
2 dated earlier
1910.12037 (2019-10)
Region Mutual Information Loss for Semantic Segmentation
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
get_seg_hrnet_w18s 1 other paper
1 later
2307.07245 (2023-07)
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation
get_seg_hrnet_w48 1 other paper
1 later
2307.07245 (2023-07)
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

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

Repositories linked to this paper

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

Abstract

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012.

For agents

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

get_harvested_code_for_paper("2106.01226")
get_code_for_paper("2106.01226")
have("2106.01226")

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

curl https://syntology.ai/api/ran/2106.01226.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.01226.svg)](https://syntology.ai/paper/2106.01226)

Connect an agent — have() is free.