SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.04732 · ICLR · 2022

A UNIFIED APPROACH TO SEMI-SUPERVISED LEARNING AND DOMAIN ADAPTATION

Kihyuk Sohn, David Berthelot, Nicholas Carlini, Alex Kurakin, Rebecca Roelofs

arXiv · PDF · Open in the Atlas

Code that ran

15 of 20 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 2 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/2106.04732.json · badge: /api/ran/2106.04732.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
zwenyu/UniSSDA community
Papers with Code archive
6 ran · 3 no recorded run
smkim7-kr/AdaMatch-pytorch community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
yizhe-ang/AdaMatch-PyTorch community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
zysymu/AdaMatch-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Adamatch Ran
ran on a synthesized input · constructed an object; no result was computed
zysymu/AdaMatch-pytorch/adamatch.py
code served (permissive licence) · get_code("8acbdc077110ba9b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, Adamatch: the run constructed the object and did not call it, so no result was computed. 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 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 import nn
import torch.nn.functional as F
import numpy as np

torch.manual_seed(0)

# Define a simple encoder
class SimpleEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(3, 8)
    
    def forward(self, x):
        return F.relu(self.fc(x))

# Define a simple classifier
class SimpleClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(8, 2)
    
    def forward(self, x):
        return self.fc(x)

# Create encoder and classifier
encoder = SimpleEncoder()
classifier = SimpleClassifier()

# Create dataloaders as lists of (data, labels) tuples
# source_dataloader_weak: batch size 2
source_dataloader_weak = [
    (torch.randn(2, 3), torch.randint(0, 2, (2,))),
    (torch.randn(2, 3), torch.randint(0, 2, (2,))),
]

# source_dataloader_strong: batch size 2
source_dataloader_strong = [
    (torch.randn(2, 3), torch.randint(0, 2, (2,))),
    (torch.randn(2, 3), torch.randint(0, 2, (2,))),
]

# target_dataloader_weak: batch size 6 (3 * source batch size)
target_dataloader_weak = [
    (torch.randn(6, 3), torch.randint(0, 2, (6,))),
    (torch.randn(6, 3), torch.randint(0, 2, (6,))),
]

# target_dataloader_strong: batch size 6 (3 * source batch size)
target_dataloader_strong = [
    (torch.randn(6, 3), torch.randint(0, 2, (6,))),
    (torch.randn(6, 3), torch.randint(0, 2, (6,))),
]

# target_dataloader_test: batch size 2
target_dataloader_test = [
    (torch.randn(2, 3), torch.randint(0, 2, (2,))),
    (torch.randn(2, 3), torch.randint(0, 2, (2,))),
]

# Hyperparameters dictionary
hyperparams = {
    'learning_rate': 0.001,
    'weight_decay': 1e-4,
    'step_scheduler': True,
    'tau': 0.95,
}

# Create save path
save_path = '/tmp/adamatch_model.pt'

# Define ARGS
ARGS = {
    'encoder': encoder,
    'classifier': classifier,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, seaborn, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Adamatch — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Adamatch 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
Algorithm Ran
ran on a synthesized input · constructed an object; no result was computed
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("39253084070f2f95")
How it ran

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

Classifier Ran
ran on a synthesized input · constructed an object; no result was computed
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("9a932222d08965d6")
How it ran

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

GradReverse Ran
ran on a synthesized input · constructed an object; no result was computed
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("2b47a2ddfc97b026")
How it ran

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

LookaheadAdam Ran
ran on a synthesized input
smkim7-kr/AdaMatch-pytorch/src/optimizer.py
code served (permissive licence) · get_code("c9f6230a51d9b5e9")
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 Lookahead. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a small model with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = torch.relu(self.linear1(x))
        x = self.linear2(x)
        return x

model = SimpleModel()
params = model.parameters()

ARGS = {
    'params': params,
    'alpha': 0.5,
    'k': 6,
}
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 Lookahead — a Lookahead output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Lookahead 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
accuracy Ran
ran on a synthesized input
smkim7-kr/AdaMatch-pytorch/src/utils.py
code served (permissive licence) · get_code("4c0ed8a3ffc26a8b")
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 torch

torch.manual_seed(0)

# The function expects:
# - output: a tensor with topk method, should be logits/scores (batch_size x num_classes)
# - target: a tensor with size(0) method and reshape/expand_as methods (batch_size,)
# - topk: tuple of integers (default (1,))

batch_size = 2
num_classes = 4

# Create output tensor (batch_size x num_classes)
output = torch.randn(batch_size, num_classes)

# Create target tensor (batch_size,) with class indices
target = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    'output': output,
    'target': target,
    'topk': (1,)
}
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
conv3x3 Ran
ran; our contract draft was wrong, not the code
smkim7-kr/AdaMatch-pytorch/models.py
pointer only (licence: MIT); the stored copy get_code serves, from DaikiTanak/manifold_mixup, is pointer only (licence: NONE) · get_code("00e569acd6b45ef0")
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 DaikiTanak/manifold_mixup, 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.

cosine_schedule Ran
ran on a synthesized input
yizhe-ang/AdaMatch-PyTorch/trainers/utils.py
code served (permissive licence) · get_code("90da0a5322508429")
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 float, 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 math

def cosine_schedule(iter: int, max_iter: int=None, decay: float=None):
    slope = math.acos(decay)
    return math.cos(slope * iter / max_iter)

ARGS = {
    "iter": 5,
    "max_iter": 100,
    "decay": 0.5
}
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 float, 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
get_logger Ran
ran on a synthesized input
smkim7-kr/AdaMatch-pytorch/src/logger.py
code served (permissive licence) · get_code("6066adc7a58afde6")
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 Logger. 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 logging

formatter = logging.Formatter('[%(asctime)s] [%(name)s] [%(levelname)s] %(message)s')

def get_logger(name, level=logging.DEBUG):
    logger = logging.getLogger(name)
    logger.handlers.clear()
    logger.setLevel(level)
    ch = logging.StreamHandler()
    ch.setLevel(level)
    ch.setFormatter(formatter)
    logger.addHandler(ch)
    return logger

ARGS = {
    'name': 'test_logger',
    'level': logging.INFO
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
grad_reverse Ran
ran, honoured the contract we drafted
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("568eece08bf61ac5")
How it ran

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

inv_lr_scheduler Ran
ran; our contract draft was wrong, not the code
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("f069b56fa07b8d15")
How it ran

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

load_model Ran
ran on a synthesized input
smkim7-kr/AdaMatch-pytorch/models.py
code served (permissive licence) · get_code("33836088c3046a9e")
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 Wide_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)

class Args:
    def __init__(self):
        self.num_classes = 10

ARGS = {
    'args': Args()
}
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 Wide_ResNet — a Wide_ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Wide_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
make_scheduler Ran
ran on a synthesized input
smkim7-kr/AdaMatch-pytorch/src/scheduler.py
code served (permissive licence) · get_code("69813457472b3348")
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 GradualWarmupScheduler. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.optim as optim
import torch.optim.lr_scheduler as lrs

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model and optimizer
model = SimpleModel()
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Create args object with required attributes
class Args:
    def __init__(self):
        self.decay_type = 'step_warmup'
        self.epoch = 90
        self.epochs = 100

args = Args()

ARGS = {
    'args': args,
    'optimizer': optimizer
}
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 GradualWarmupScheduler — a GradualWarmupScheduler output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GradualWarmupScheduler 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
pretrain Ran
ran on a synthesized input · constructed an object; no result was computed
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("08c87afb301070b5")
How it ran

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

unnormalize_img Ran
ran on a synthesized input
yizhe-ang/AdaMatch-PyTorch/trainers/utils.py
code served (permissive licence) · get_code("33cf5d0c4a76211f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (4, 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

torch.manual_seed(0)

# Create a small image tensor with shape (C, H, W) where C=4 channels
img = torch.randn(4, 2, 3)

# Create mean and std as lists (will be converted to tensors inside the function)
mean = [0.5, 0.3, 0.2, 0.1]
std = [0.2, 0.15, 0.1, 0.25]

ARGS = {
    "img": img,
    "mean": mean,
    "std": std,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (4, 2, 3) — shape (4, 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
AdaMatch Not yet run
unverified (harvested, no recorded run)
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("4fcf58e0e0f0df7d")
How it ran

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

AdaMatch_loss Not yet run
unverified (harvested, no recorded run)
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("3d16ce208399a304")
How it ran

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

Over9000 Not yet run
unverified (harvested, no recorded run)
smkim7-kr/AdaMatch-pytorch/src/optimizer.py
code served (permissive licence) · get_code("0f150f7b3d28baf0")
How it ran

no invocation recorded.

make_optimizer Not yet run
unverified (harvested, no recorded run)
smkim7-kr/AdaMatch-pytorch/src/optimizer.py
code served (permissive licence) · get_code("0c2325bd115425e9")
How it ran

no invocation recorded.

weights_init Not yet run
unverified (harvested, no recorded run)
zwenyu/UniSSDA/algorithms/algorithms.py
pointer only (licence: NONE) · get_code("fad33bd48f70436d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwenyu/UniSSDA 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 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 2 later) and 11 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 74 other papers
24 dated earlier, 1 the same month, 49 later · 5 only as an assembly brick
1605.07146 (2016-05)
Wide Residual Networks
1707.01629 (2017-07)
Dual Path Networks
1802.05668 (2018-02)
Model compression via distillation and quantization
and 71 more not named here
grad_reverse
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
2006.12087 (2020-06)
Progressive Graph Learning for Open-Set Domain Adaptation
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
2202.06174 (2022-02)
Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
get_logger 2 other papers
2 dated earlier
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
inv_lr_scheduler
brick of this paper's assembly: scheduler
2 other papers
2 dated earlier · 1 only as an assembly brick
1904.06487 (2019-04)
Semi-supervised Domain Adaptation via Minimax Entropy
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
Algorithm
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
Classifier
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
GradReverse
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
pretrain
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
weights_init
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

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

We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a unified solution for unsupervised domain adaptation (UDA), semi-supervised learning (SSL), and semi-supervised domain adaptation (SSDA). In an extensive experimental study, we compare its behavior with respective state-of-the-art techniques from SSL, SSDA, and UDA and find that AdaMatch either matches or significantly exceeds the state-of-the-art in each case using the same hyper-parameters regardless of the dataset or task. For example, AdaMatch nearly doubles the accuracy compared to that of the prior state-of-the-art on the UDA task for DomainNet and even exceeds the accuracy of the prior state-of-the-art obtained with pre-training by 6.4% when AdaMatch is trained completely from scratch. Furthermore, by providing AdaMatch with just one labeled example per class from the target domain (i.e., the SSDA setting), we increase the target accuracy by an additional 6.1%, and with 5 labeled examples, by 13.6%. 1

For agents

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

get_harvested_code_for_paper("2106.04732")
get_code_for_paper("2106.04732")
have("2106.04732")

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

curl https://syntology.ai/api/ran/2106.04732.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.04732.svg)](https://syntology.ai/paper/2106.04732)

Connect an agent — have() is free.