SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.07340 · 2023

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

arXiv · PDF · Open in the Atlas

Code that ran

8 of 13 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, 0 violated it and 4 have no contract verdict; 4 failures of our instrument; 5 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/2301.07340.json · badge: /api/ran/2301.07340.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
Jin-Ying/GTA-Seg canonical (classifier label)
classifier basis not recorded on the link
8 ran · 5 no recorded run
FunctionStatusWhere it lives
compute_rce_loss Ran
ran; our contract draft was wrong, not the code
Jin-Ying/GTA-Seg/gta/utils/loss_helper.py
code served (permissive licence) · get_code("ab90969959ef1daa")
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
from torch.nn import functional as F

torch.manual_seed(0)

# Create small tensors for the function
batch_size = 2
num_classes = 4
height = 3
width = 5

# predict: shape (b, c, h, w) - logits before softmax
predict = torch.randn(batch_size, num_classes, height, width)

# target: shape (b, h, w) - class indices, with 255 as ignore index
target = torch.randint(0, num_classes, (batch_size, height, width))
# Add some 255 values to test the ignore index logic
target[0, 0, 0] = 255
target[1, 1, 1] = 255

ARGS = {
    "predict": predict,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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_unsupervised_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Jin-Ying/GTA-Seg/gta/utils/loss_helper.py
code served (permissive licence) · get_code("00f3224921ae6a19")
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) and returned Tensor, 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors with distinct dimensions
batch_size = 2
num_class = 4
h = 3
w = 5

# predict: logits from model, shape (batch_size, num_class, h, w)
predict = torch.randn(batch_size, num_class, h, w)

# pred_teacher: teacher model predictions, shape (batch_size, num_class, h, w)
pred_teacher = torch.randn(batch_size, num_class, h, w)

# target: ground truth labels, shape (batch_size, h, w)
# Values should be class indices (0 to num_class-1) or 255 (ignore index)
target = torch.randint(0, num_class, (batch_size, h, w))
# Add some 255 values (ignore index)
target[0, 0, 0] = 255
target[1, 1, 1] = 255

# percent: percentile threshold for entropy filtering
percent = 50

ARGS = {
    "predict": predict,
    "target": target,
    "percent": percent,
    "pred_teacher": pred_teacher,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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_unsupervised_loss_conf Ran
ran on a synthesized input
Jin-Ying/GTA-Seg/gta/utils/loss_helper.py
code served (permissive licence) · get_code("e6dac9d663788f54")
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. 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
from torch.nn import functional as F

torch.manual_seed(0)

# Create small tensors with distinct dimensions
batch_size = 2
num_class = 4
h = 3
w = 5

# predict: logits from model, shape (batch_size, num_class, h, w)
predict = torch.randn(batch_size, num_class, h, w)

# pred_teacher: teacher model predictions, same shape as predict
pred_teacher = torch.randn(batch_size, num_class, h, w)

# target: segmentation labels with shape (batch_size, h, w)
# Mix of class indices (0-3) and 255 (ignore index)
target = torch.tensor([
    [[0, 1, 2, 255, 3],
     [1, 2, 3, 0, 1],
     [2, 3, 0, 1, 255]],
    [[3, 0, 1, 2, 3],
     [0, 1, 255, 3, 0],
     [1, 2, 3, 0, 1]]
], dtype=torch.long)

# percent: confidence threshold percentile (0-100)
percent = 50

ARGS = {
    "predict": predict,
    "target": target,
    "percent": percent,
    "pred_teacher": pred_teacher
}
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 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
Jin-Ying/GTA-Seg/gta/models/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
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) and returned Conv2d. 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)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
Jin-Ying/GTA-Seg/gta/models/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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) and returned Conv2d. 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 = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
generate_class_mask Ran
ran on a synthesized input
Jin-Ying/GTA-Seg/gta/dataset/augmentation.py
code served (permissive licence) · get_code("eaeada2a036c97a0")
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 (8,) 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 a small pseudo_labels tensor with class indices
# Shape: (batch_size,) with values representing class labels
pseudo_labels = torch.tensor([0, 1, 2, 0, 1, 2, 0, 1], dtype=torch.long)

ARGS = {
    "pseudo_labels": pseudo_labels,
}
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 (8,) — shape (8,) 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
generate_cutout_mask Ran
ran on a synthesized input
Jin-Ying/GTA-Seg/gta/dataset/augmentation.py
code served (permissive licence) · get_code("d939e70ad62258fb")
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 int, shape (4, 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 numpy as np

torch.manual_seed(0)
np.random.seed(0)

ARGS = {
    "img_size": (4, 3),
    "ratio": 2
}
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 2, dtype family int, shape (4, 3) — shape (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
generate_unsup_data Ran
ran on a synthesized input
Jin-Ying/GTA-Seg/gta/dataset/augmentation.py
code served (permissive licence) · get_code("d5923e5cf8631474")
How it ran

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

import torch
import numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create tiny tensors for testing
batch_size = 2
channels = 3
im_h = 4
im_w = 5

# data: (batch_size, channels, height, width)
data = torch.randn(batch_size, channels, im_h, im_w)

# target: (batch_size, height, width) - semantic segmentation labels
target = torch.randint(0, 10, (batch_size, im_h, im_w))
target[0, 0, 0] = 255  # Some ignore label

# logits: (batch_size, height, width) or similar shape
logits = torch.randn(batch_size, im_h, im_w)

# Test with 'cutout' mode
mode = 'cutout'

ARGS = {
    'data': data,
    'target': target,
    'logits': logits,
    'mode': mode
}
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 tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_coco_semi_loader Not yet run
unverified (harvested, no recorded run)
Jin-Ying/GTA-Seg/gta/dataset/coco.py
code served (permissive licence) · get_code("629f4c1332cce01e")
How it ran

no invocation recorded.

build_transfrom Not yet run
unverified (harvested, no recorded run)
Jin-Ying/GTA-Seg/gta/dataset/coco.py
code served (permissive licence) · get_code("54d11fde9c12abd0")
How it ran

no invocation recorded.

build_transfrom Not yet run
unverified (harvested, no recorded run)
Jin-Ying/GTA-Seg/gta/dataset/cityscapes.py
code served (permissive licence) · get_code("763f9c17ccbeb5ef")
How it ran

no invocation recorded.

get_loader Not yet run
unverified (harvested, no recorded run)
Jin-Ying/GTA-Seg/gta/dataset/builder.py
code served (permissive licence) · get_code("85056ce7849ad6da")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
Jin-Ying/GTA-Seg/gta/models/resnet.py
code served (permissive licence) · get_code("aa86d25496cd605b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 9 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 4 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
conv1x1 431 other papers
236 dated earlier, 3 the same month, 183 later, 8 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
152 dated earlier, 2 the same month, 150 later, 7 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
compute_unsupervised_loss 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
2203.03884 (2022-03)
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
2403.06462 (2024-03)
Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation
compute_rce_loss 2 other papers
1 later, 1 same year, order not determinable
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
2403.06462 (2024-03)
Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation
build_transfrom 1 other paper
1 same year, order not determinable
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
generate_class_mask 1 other paper
1 same year, order not determinable
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
generate_cutout_mask 1 other paper
1 same year, order not determinable
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
generate_unsup_data 1 other paper
1 same year, order not determinable
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation
resnet18 1 other paper
1 same year, order not determinable
Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper (2023 (year only))
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic 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

Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data. To effectively leverage the unlabeled data, pseudo labeling, along with the teacher-student framework, is widely adopted in semi-supervised semantic segmentation. Though proved to be effective, this paradigm suffers from incorrect pseudo labels which inevitably exist and are taken as auxiliary training data. To alleviate the negative impact of incorrect pseudo labels, we delve into the current Semi-Supervised Semantic Segmentation frameworks. We argue that the unlabeled data with pseudo labels can facilitate the learning of representative features in the feature extractor, but it is unreliable to supervise the mask predictor. Motivated by this consideration, we propose a novel framework, Gentle Teaching Assistant (GTA-Seg) to disentangle the effects of pseudo labels on feature extractor and mask predictor of the student model. Specifically, in addition to the original teacher-student framework, our method introduces a teaching assistant network which directly learns from pseudo labels generated by the teacher network. The gentle teaching assistant (GTA) is coined gentle since it only transfers the beneficial feature representation knowledge in the feature extractor to the student model in an Exponential Moving Average (EMA) manner, protecting the student model from the negative influences caused by unreliable pseudo labels in the mask predictor. The student model is also supervised by reliable labeled data to train an accurate mask predictor, further facilitating feature representation. Extensive experiment results on benchmark datasets validate that our method shows competitive performance against previous methods. Code is available at https://github.com/Jin-Ying/GTA-Seg.

For agents

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

get_harvested_code_for_paper("2301.07340")
get_code_for_paper("2301.07340")
have("2301.07340")

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

curl https://syntology.ai/api/ran/2301.07340.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.07340.svg)](https://syntology.ai/paper/2301.07340)

Connect an agent — have() is free.