SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.05464 · 2017

Adversarial Discriminative Domain Adaptation

Kate Saenko, Trevor Darrell, Judy Hoffman, Eric Tzeng

arXiv · PDF · Open in the Atlas

Code that ran

14 of 48 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 6 have no contract verdict; 7 failures of our instrument; 34 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/1702.05464.json · badge: /api/ran/1702.05464.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
adapt-python/adapt community
Papers with Code archive
4 ran · 2 no recorded run
kevinmusgrave/pytorch-adapt community
Papers with Code archive
1 ran · 22 no recorded run
jvanvugt/pytorch-domain-adaptation community
Papers with Code archive
1 ran · 2 no recorded run
Backdrop9019/adda_pytorch-pseudo-mixup- community
Papers with Code archive
1 ran · 2 no recorded run
happen2me/adda_pytorch community
Papers with Code archive
1 ran · 1 no recorded run
anglihust/Unsupervised-vessel-segmentation community
Papers with Code archive
1 ran · 1 no recorded run
mashaan14/ADDA-toy community
Papers with Code archive
1 ran · 0 no recorded run
Backdrop9019/pytorch_adda_mixup community
Papers with Code archive
1 ran · 0 no recorded run
Fujiki-Nakamura/ADDA.PyTorch community
Papers with Code archive
1 ran · 0 no recorded run
kevin851066/Deep_Learning_for_Computer_Vision community
Papers with Code archive
1 ran · 0 no recorded run
thuml/Transfer-Learning-Library community
Papers with Code archive
1 ran · 0 no recorded run
caoquanjie/ADDA-master community
Papers with Code archive
0 ran · 2 no recorded run
corenel/pytorch-adda community
Papers with Code archive
0 ran · 1 no recorded run
Carl0520/ADDA-pytorch community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Discriminator Ran
ran on a synthesized input · constructed an object; no result was computed
mashaan14/ADDA-toy/models.py
pointer only (licence: NONE) · get_code("7ee0559533467085")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mashaan14/ADDA-toy 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.

Discriminator Ran
ran on a synthesized input · constructed an object; no result was computed
Backdrop9019/pytorch_adda_mixup/models/models.py
pointer only (licence: NONE) · get_code("8834a2ebbe444d53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Backdrop9019/pytorch_adda_mixup 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.

Discriminator Ran
ran on a synthesized input · constructed an object; no result was computed
Fujiki-Nakamura/ADDA.PyTorch/models.py
pointer only (licence: NONE) · get_code("e8e38bfc623d704e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Fujiki-Nakamura/ADDA.PyTorch 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.

Discriminator Ran
ran on a synthesized input · constructed an object; no result was computed
kevin851066/Deep_Learning_for_Computer_Vision/hw3-kevin851066/ADDA/SM_M/ADDA.py
pointer only (licence: NONE) · get_code("ebf44e526ae75e68")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kevin851066/Deep_Learning_for_Computer_Vision 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.

DomainAdversarialLoss Ran
ran on a synthesized input
thuml/Transfer-Learning-Library/tllib/alignment/adda.py
code served (permissive licence) · get_code("7bb28fb79002a53d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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 torch
import torch.nn as nn

# INIT_ARGS: DomainAdversarialLoss.__init__ takes no parameters
INIT_ARGS = {}

# ARGS: forward method takes domain_pred and domain_label
# domain_pred should be shape (minibatch,) with values in [0, 1] for binary_cross_entropy
# domain_label is either 'source' or 'target'

domain_pred = torch.tensor([0.7, 0.3, 0.8, 0.2, 0.6])  # minibatch=5
domain_label = 'source'

ARGS = {
    'domain_pred': domain_pred,
    'domain_label': domain_label
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
check_network Ran
ran; our contract draft was wrong, not the code
adapt-python/adapt/adapt/feature_based/_adda.py
code served (permissive licence) · get_code("dfe3c0d123bc7830")
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 Functional. 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 tensorflow as tf
from tensorflow.keras import Model, layers
import numpy as np

# Create a minimal but valid Keras Model
inputs = tf.keras.Input(shape=(4,))
x = layers.Dense(8, activation='relu')(inputs)
outputs = layers.Dense(3, activation='linear')(x)
network = Model(inputs=inputs, outputs=outputs)

# Build the network by calling it once
network.build((None, 4))
network.compile(optimizer='adam', loss='mse')

# Set some weights so the network has trainable parameters
network.set_weights([
    np.random.randn(4, 8).astype(np.float32),
    np.random.randn(8).astype(np.float32),
    np.random.randn(8, 3).astype(np.float32),
    np.random.randn(3).astype(np.float32),
])

ARGS = {
    'network': network,
    'copy': True,
    'name': 'test_network',
    'force_copy': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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_default_discriminator Ran
ran; our contract draft was wrong, not the code
adapt-python/adapt/adapt/feature_based/_adda.py
code served (permissive licence) · get_code("60cfae1e4c765da8")
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 Sequential. 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 tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.initializers import GlorotUniform

# Define ARGS dict with all parameters for get_default_discriminator
ARGS = {
    'name': 'test_discriminator',
    'state': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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_default_encoder Ran
ran; our contract draft was wrong, not the code
adapt-python/adapt/adapt/feature_based/_adda.py
code served (permissive licence) · get_code("ba83013d36128386")
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 Sequential. 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 tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.initializers import GlorotUniform

ARGS = {
    "name": "test_encoder",
    "state": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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_default_task Ran
ran; our contract draft was wrong, not the code
adapt-python/adapt/adapt/feature_based/_adda.py
code served (permissive licence) · get_code("4078865962ffaf59")
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 Sequential. 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 tensorflow as tf
from tensorflow.keras import Sequential, Model
from tensorflow.keras.layers import Layer, Dense, Flatten, Input
from tensorflow.keras.initializers import GlorotUniform

ARGS = {
    "activation": "sigmoid",
    "name": "test_model",
    "state": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
loop_iterable Ran
ran; our contract draft was wrong, not the code
jvanvugt/pytorch-domain-adaptation/adda.py
code served (permissive licence) · get_code("af8de7283d2b0b9e")
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 generator. 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)

# loop_iterable takes an iterable and yields from it in an infinite loop
# The function uses: iteration (for loop via yield from)
# We need to provide a simple iterable

iterable = [1, 2, 3, 4, 5]

ARGS = {
    "iterable": iterable
}
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 generator — a generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a generator 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_cuda Ran
ran, honoured the contract we drafted
happen2me/adda_pytorch/core/adapt.py
pointer only (licence: NONE) · get_code("4c5ddb71c68be51a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, happen2me/adda_pytorch 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.

mixup_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Backdrop9019/adda_pytorch-pseudo-mixup-/core/adapt.py
pointer only (licence: NONE) · get_code("084dfb3d87216615")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Backdrop9019/adda_pytorch-pseudo-mixup- 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.

tfADDA Ran
ran on a synthesized input · constructed an object; no result was computed
anglihust/Unsupervised-vessel-segmentation/models.py
code served (permissive licence) · get_code("bfd00c4055fd2adc")
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, tfADDA: the run constructed the object and did not call it, so no result was computed. 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 tensorflow as tf
from keras import backend as K

class Config:
    def __init__(self):
        self.multi_fusion = True

def swish(x):
    return K.sigmoid(x) * x

config = Config()

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tfADDA — 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 tfADDA 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
wrap_keys Ran
ran; our contract draft was wrong, not the code
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("622c3f05a9b70b22")
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 dict. 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

def c_f_is_list_or_tuple(x):
    """Stand-in for c_f.is_list_or_tuple"""
    return isinstance(x, (list, tuple))

# Monkey-patch the function's dependency
import sys
from types import SimpleNamespace
c_f = SimpleNamespace(is_list_or_tuple=c_f_is_list_or_tuple)

# Test case 1: dict input with prefix and suffix
x_dict = {
    'key1': 'value1',
    'key2': 'value2',
    'nested': {'a': 1}
}
prefix_str = 'pre_'
suffix_str = '_post'

ARGS = {
    'x': x_dict,
    'prefix': prefix_str,
    'suffix': suffix_str
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
ADDA Not yet run
unverified (harvested, no recorded run)
adapt-python/adapt/adapt/feature_based/_adda.py
code served (permissive licence) · get_code("ce9e1a5eac1050da")
How it ran

no invocation recorded.

ADDAHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("25e34a726b2ba605")
How it ran

no invocation recorded.

BaseAdaptDeep Not yet run
unverified (harvested, no recorded run)
adapt-python/adapt/adapt/feature_based/_adda.py
code served (permissive licence) · get_code("91edb2b8f17a72f6")
How it ran

no invocation recorded.

BaseConditionHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("4b4ebf6d67718656")
How it ran

no invocation recorded.

BaseFeaturesHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("2607dc161f092df7")
How it ran

no invocation recorded.

BaseHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("ca7d95b46428e282")
How it ran

no invocation recorded.

BaseWrapperHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("f4f0abb8e8238039")
How it ran

no invocation recorded.

CLossHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("f4b49872d61ca7cb")
How it ran

no invocation recorded.

ChainHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("46a87df5beca7a35")
How it ran

no invocation recorded.

DLogitsHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("433003a2c8fc7f61")
How it ran

no invocation recorded.

EmptyHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("97400f2418c74bce")
How it ran

no invocation recorded.

FalseHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("31542fd54d3ac9ac")
How it ran

no invocation recorded.

FeaturesAndLogitsHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("040844c8bd2ffcae")
How it ran

no invocation recorded.

FeaturesChainHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("ba9568d0ea5cbcee")
How it ran

no invocation recorded.

FeaturesHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("ad7cd588e5081b5d")
How it ran

no invocation recorded.

FeaturesWithGradAndDetachedHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("72b333545ead7d03")
How it ran

no invocation recorded.

FrozenModelHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("724735f6d9545589")
How it ran

no invocation recorded.

GANHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("3bf49b3d9b8d635e")
How it ran

no invocation recorded.

LogitsHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("4bd3dad9e4078393")
How it ran

no invocation recorded.

StrongDHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("08838ca55f39ac9f")
How it ran

no invocation recorded.

TrueHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("40469ce9b9b8e75d")
How it ran

no invocation recorded.

ZeroLossHook Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("ff6a75be2bbdf375")
How it ran

no invocation recorded.

check_keys_are_present Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("7cbe490d83bf8263")
How it ran

no invocation recorded.

concat_ad_loss_2 Not yet run
unverified (harvested, no recorded run)
caoquanjie/ADDA-master/adda.py
pointer only (licence: NONE) · get_code("a382b74025c113e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, caoquanjie/ADDA-master 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.

discriminator Not yet run
unverified (harvested, no recorded run)
caoquanjie/ADDA-master/adda.py
pointer only (licence: NONE) · get_code("566bf3a9068aa745")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, caoquanjie/ADDA-master 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.

eval_src Not yet run
unverified (harvested, no recorded run)
Backdrop9019/adda_pytorch-pseudo-mixup-/core/adapt.py
pointer only (licence: NONE) · get_code("ae0275061ef16144")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Backdrop9019/adda_pytorch-pseudo-mixup- 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.

main Not yet run
unverified (harvested, no recorded run)
jvanvugt/pytorch-domain-adaptation/adda.py
code served (permissive licence) · get_code("1bd934517a6aa265")
How it ran

no invocation recorded.

replace_mapped_keys Not yet run
unverified (harvested, no recorded run)
kevinmusgrave/pytorch-adapt/src/pytorch_adapt/hooks/adda.py
code served (permissive licence) · get_code("2a961204ae724b34")
How it ran

no invocation recorded.

set_requires_grad Not yet run
unverified (harvested, no recorded run)
jvanvugt/pytorch-domain-adaptation/adda.py
code served (permissive licence) · get_code("b4339c04b8867835")
How it ran

no invocation recorded.

swish Not yet run
unverified (harvested, no recorded run)
anglihust/Unsupervised-vessel-segmentation/models.py
code served (permissive licence) · get_code("12ddf95e9fccb3c4")
How it ran

no invocation recorded.

train_tgt Not yet run
unverified (harvested, no recorded run)
corenel/pytorch-adda/core/adapt.py
code served (permissive licence) · get_code("b2531ab289d6f8e9")
How it ran

no invocation recorded.

train_tgt Not yet run
unverified (harvested, no recorded run)
happen2me/adda_pytorch/core/adapt.py
pointer only (licence: NONE) · get_code("8ab9e937c7ff7cd1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, happen2me/adda_pytorch 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.

train_tgt Not yet run
unverified (harvested, no recorded run)
Backdrop9019/adda_pytorch-pseudo-mixup-/core/adapt.py
pointer only (licence: NONE) · get_code("84d421fc6e4a0800")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Backdrop9019/adda_pytorch-pseudo-mixup- 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.

train_tgt Not yet run
unverified (harvested, no recorded run)
Carl0520/ADDA-pytorch/core/adapt.py
pointer only (licence: NONE) · get_code("1c6d0180357995cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Carl0520/ADDA-pytorch 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 48 samples lifted from this paper's linked repositories, 48 carry a function identity and 0 do not. Of the 47 distinct functions with an identity, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 2 later) and 40 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
BaseAdaptDeep
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
1607.01719 (2016-07)
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
check_network
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
1607.01719 (2016-07)
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
get_default_discriminator
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
1607.01719 (2016-07)
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
get_default_encoder
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
1607.01719 (2016-07)
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
get_default_task
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
1607.01719 (2016-07)
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
make_cuda
brick of this paper's assembly: helper
1 other paper
1 later
2410.04424 (2024-10)
DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs
swish
brick of this paper's assembly: helper
1 other paper
1 later
1703.06870 (2017-03)
Mask R-CNN

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

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several adversarial approaches to unsupervised domain adaptation have recently been introduced, which reduce the difference between the training and test domain distributions and thus improve generalization performance. Prior generative approaches show compelling visualizations, but are not optimal on discriminative tasks and can be limited to smaller shifts. Prior discriminative approaches could handle larger domain shifts, but imposed tied weights on the model and did not exploit a GAN-based loss. We first outline a novel generalized framework for adversarial adaptation, which subsumes recent state-of-the-art approaches as special cases, and we use this generalized view to better relate the prior approaches. We propose a previously unexplored instance of our general framework which combines discriminative modeling, untied weight sharing, and a GAN loss, which we call Adversarial Discriminative Domain Adaptation (ADDA). We show that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and demonstrate the promise of our approach by exceeding state-of-the-art unsupervised adaptation results on standard cross-domain digit classification tasks and a new more difficult cross-modality object classification task.

For agents

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

get_harvested_code_for_paper("1702.05464")
get_code_for_paper("1702.05464")
have("1702.05464")

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

curl https://syntology.ai/api/ran/1702.05464.json

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

[![Syntology run record](https://syntology.ai/api/ran/1702.05464.svg)](https://syntology.ai/paper/1702.05464)

Connect an agent — have() is free.