SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_28150 · AAAI · 2024

DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels

Ming Yan, Haoran Liu, Dezhong Peng, Xu Wang, Ying Ma, Yingke Chen

Code that ran

16 of 20 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 9 have no contract verdict; 7 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/aaai_28150.json · badge: /api/ran/aaai_28150.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
lhrrrrrr/DiDA canonical (classifier label)
classifier basis: census
16 ran · 4 no recorded run
FunctionStatusWhere it lives
AutoContrast Ran
ran; our contract draft was wrong, not the code
lhrrrrrr/DiDA/utils/randaugment.py
code served (permissive licence) · get_code("4a0ac9d611e018bc")
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 Image. 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 PIL
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw

# Create a simple PIL Image for testing
# AutoContrast expects a PIL Image object as the first parameter
img = PIL.Image.new('RGB', (4, 3), color=(128, 100, 150))

# The second parameter is unused (indicated by _), so we can pass None or any value
second_param = None

ARGS = {
    'img': img,
    '_': second_param,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
AutoContrast Ran
ran; our contract draft was wrong, not the code
lhrrrrrr/DiDA/transforms/RandAugment.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from MaxH1996/FedXDS, is pointer only (licence: NONE) · get_code("c6e7c3451c85404f")
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 MaxH1996/FedXDS, 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.

Brightness Ran
ran; our contract draft was wrong, not the code
lhrrrrrr/DiDA/transforms/RandAugment.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from MaxH1996/FedXDS, is pointer only (licence: NONE) · get_code("0d1a8d6ce2015fc7")
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 MaxH1996/FedXDS, 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.

Brightness Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lhrrrrrr/DiDA/utils/randaugment.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from zhengzhang37/lecodu, is pointer only (licence: NONE) · get_code("61ed09bbdb8adb72")
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 zhengzhang37/lecodu, 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.

Color Ran
ran; our contract draft was wrong, not the code
lhrrrrrr/DiDA/transforms/RandAugment.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from MaxH1996/FedXDS, is pointer only (licence: NONE) · get_code("32cb3f5760fa593e")
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 MaxH1996/FedXDS, 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.

Color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lhrrrrrr/DiDA/utils/randaugment.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from zhengzhang37/lecodu, is pointer only (licence: NONE) · get_code("5e4ee5c45933ae09")
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 zhengzhang37/lecodu, 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.

compute_pda_loss Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils_loss.py
code served (permissive licence) · get_code("8a480fc4c11faeb7")
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)

# Analyze the function:
# - feats_q: used with torch.mm(feats_q, prototypes_src.t()) -> shape (batch, feat_dim)
# - feats_q1: used with torch.mm(feats_q1, prototypes_src.t()) -> shape (batch, feat_dim)
# - prototypes_src: used with .t() and torch.mm -> shape (num_prototypes, feat_dim)
# - prototypes_tar: used with .t() and torch.mm -> shape (num_prototypes, feat_dim)

batch_size = 2
feat_dim = 4
num_prototypes = 3

feats_q = torch.randn(batch_size, feat_dim)
feats_q1 = torch.randn(batch_size, feat_dim)
prototypes_src = torch.randn(num_prototypes, feat_dim)
prototypes_tar = torch.randn(num_prototypes, feat_dim)

ARGS = {
    "feats_q": feats_q,
    "feats_q1": feats_q1,
    "prototypes_src": prototypes_src,
    "prototypes_tar": prototypes_tar,
}
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
confidence_init Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils_pll.py
code served (permissive licence) · get_code("f23d7ff55fedaa81")
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 3, dtype family float; no output shape is stated. 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 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

torch.manual_seed(0)

# Create mock dataset objects with labels attribute
class MockDataset:
    def __init__(self, labels):
        self.labels = labels

# Create source and target labels as tensors
# Shape: (batch_size, num_classes) - using 2 samples, 4 classes
source_labels = torch.tensor([
    [2, 1, 0, 0],
    [0, 3, 1, 0]
], dtype=torch.long)

target_labels = torch.tensor([
    [1, 2, 0, 1],
    [0, 0, 2, 1]
], dtype=torch.long)

# Create the mock dataset loaders dictionary
dset_loaders = {
    'source_tr_nobatch': MockDataset(source_labels),
    'target_tr_nobatch': MockDataset(target_labels)
}

ARGS = {
    'dset_loaders': dset_loaders
}
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 3, 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
confidence_update Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils_pll.py
code served (permissive licence) · get_code("3c6ed8faa90d18a4")
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, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors
batch_size = 2
num_classes = 4

# confidence: a tensor tracking confidence scores, shape (batch_size, num_classes)
confidence = torch.rand(batch_size, num_classes)

# logits: raw model outputs, shape (batch_size, num_classes)
logits = torch.randn(batch_size, num_classes)

# plLabel: pseudo-labels, shape (batch_size, num_classes)
plLabel = torch.randint(0, 2, (batch_size, num_classes)).float()

# indexes: indices to update in confidence, shape (some_subset,)
indexes = torch.tensor([0, 1])

ARGS = {
    "confidence": confidence,
    "logits": logits,
    "plLabel": plLabel,
    "indexes": indexes
}
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, 4) — shape (2, 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
lhrrrrrr/DiDA/resnet.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

generate_uniform_cv_candidate_labels Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils_pll.py
code served (permissive licence) · get_code("8570d0ed718d0732")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (4, 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)

# Create small training labels as numpy array
# Labels should be in range [0, num_classes-1]
# Using 4 samples with 3 classes (0, 1, 2)
train_labels = np.array([0, 1, 2, 1], dtype=np.int64)

ARGS = {
    "train_labels": train_labels,
    "partial_rate": 0.1,
}
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 float, 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
image_shift Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils.py
code served (permissive licence) · get_code("2dd8d7e5b1087972")
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 Compose. 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
from PIL import Image
from torchvision import transforms

torch.manual_seed(0)

# Create a small test image to verify the transform works
test_image = Image.new('RGB', (300, 300), color=(73, 109, 137))

# Define ARGS with all parameters of image_shift
ARGS = {
    'resize_size': 256,
    'crop_size': 224
}

# Verify the function can be called and applied to a test image
transform = transforms.Compose([
    transforms.Resize((ARGS['resize_size'], ARGS['resize_size'])),
    transforms.ColorJitter(0.2, 0.2, 0.2, 0.1),
    transforms.RandomCrop(224),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# Test that the transform can be applied
transformed = transform(test_image)

ARGS = {
    'resize_size': 256,
    'crop_size': 224
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
image_target Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils.py
code served (permissive licence) · get_code("fcbce437a044a898")
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 Compose. 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
from torchvision import transforms
from PIL import Image

torch.manual_seed(0)

# The function image_target takes two optional parameters: resize_size and crop_size
# Looking at the function body, it uses these parameters to:
# - resize_size: passed to transforms.Resize as (resize_size, resize_size)
# - crop_size: appears in the function signature but is NOT actually used in the Compose chain
#   (the RandomCrop uses hardcoded 224 instead of the crop_size parameter)

# We'll provide reasonable default values
ARGS = {
    "resize_size": 256,
    "crop_size": 224,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
image_train Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils.py
code served (permissive licence) · get_code("620153a1ea154802")
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 Compose. 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 torchvision
from torchvision import transforms
from PIL import Image
import numpy as np

torch.manual_seed(0)

# The function image_train takes two optional parameters: resize_size and crop_size
# Both are integers with default values
# The function returns a transforms.Compose object that can be applied to images

ARGS = {
    "resize_size": 256,
    "crop_size": 224,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
resnet18 Ran
ran on a synthesized input
lhrrrrrr/DiDA/resnet.py
code served (permissive licence) · get_code("016273f8414c942a")
How it ran

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

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
update_loss_weight Ran
ran on a synthesized input
lhrrrrrr/DiDA/utils/utils_loss.py
code served (permissive licence) · get_code("be036fafac3d3517")
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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "epoch": 5,
    "max": 10
}
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 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
grad_reverse Not yet run
unverified (harvested, no recorded run)
lhrrrrrr/DiDA/resnet.py
code served (permissive licence) · get_code("9546e8417b4bdc1a")
How it ran

no invocation recorded.

make_dataset Not yet run
unverified (harvested, no recorded run)
lhrrrrrr/DiDA/data_load.py
code served (permissive licence) · get_code("bd7771071feeff38")
How it ran

no invocation recorded.

test_map Not yet run
unverified (harvested, no recorded run)
lhrrrrrr/DiDA/Trainer/trainer.py
code served (permissive licence) · get_code("1b820dc491e143c6")
How it ran

no invocation recorded.

train_model Not yet run
unverified (harvested, no recorded run)
lhrrrrrr/DiDA/Trainer/trainer.py
code served (permissive licence) · get_code("37f910aa186816fa")
How it ran

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, 0 the same month, 4 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 686 other papers
548 dated earlier, 28 later, 110 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
AutoContrast 19 other papers
9 dated earlier, 1 later, 9 same year, order not determinable
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2003.10580 (2020-03)
Meta Pseudo Labels
2104.07713 (2021-04)
Contrastive Learning with Stronger Augmentations
and 16 more not named here
Brightness 19 other papers
9 dated earlier, 1 later, 9 same year, order not determinable
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2003.10580 (2020-03)
Meta Pseudo Labels
2104.07713 (2021-04)
Contrastive Learning with Stronger Augmentations
and 16 more not named here
Color 18 other papers
9 dated earlier, 1 later, 8 same year, order not determinable
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2003.10580 (2020-03)
Meta Pseudo Labels
2104.07713 (2021-04)
Contrastive Learning with Stronger Augmentations
and 15 more not named here
AutoContrast 14 other papers
9 dated earlier, 5 same year, order not determinable · 4 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 11 more not named here
Brightness 7 other papers
2 dated earlier, 5 same year, order not determinable
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
2312.04604 (2023-12)
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World Transferable Candidate Proposal with Bounded Uncertainty
aaai_29068 (2024 (year only))
Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
and 4 more not named here
Color 7 other papers
2 dated earlier, 5 same year, order not determinable
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
2312.04604 (2023-12)
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World Transferable Candidate Proposal with Bounded Uncertainty
aaai_29068 (2024 (year only))
Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
and 4 more not named here
grad_reverse 3 other papers
3 dated earlier
1904.06487 (2019-04)
Semi-supervised Domain Adaptation via Minimax Entropy
2006.12770 (2020-06)
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
2106.02874 (2021-06)
RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
image_train 1 other paper
1 dated earlier
2207.13247 (2022-07)
Concurrent Subsidiary Supervision for Unsupervised Source-Free 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

Driven by generative AI and the Internet, there is an increasing availability of a wide variety of images, leading to the significant and popular task of cross-domain image retrieval. To reduce annotation costs and increase performance, this paper focuses on an untouched but challenging problem, i.e., cross-domain image retrieval with partial labels (PCIR). Specifically, PCIR faces great challenges due to the ambiguous supervision signal and the domain gap. To address these challenges, we propose a novel method called disambiguated domain alignment (DiDA) for cross-domain retrieval with partial labels. In detail, DiDA elaborates a novel prototypescore unitization learning mechanism (PSUL) to extract common discriminative representations by simultaneously disambiguating the partial labels and narrowing the domain gap. Additionally, DiDA proposes a prototype-based domain alignment mechanism (PBDA) to further bridge the inherent cross-domain discrepancy. Attributed to PSUL and PBDA, our DiDA effectively excavates domain-invariant discrimination for cross-domain image retrieval. We demonstrate the effectiveness of DiDA through comprehensive experiments on three benchmarks, comparing it to existing state-of-the-art methods. Code available: https://github.com/lhrrrrrr/DiDA.

For agents

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

get_harvested_code_for_paper("aaai_28150")
get_code_for_paper("aaai_28150")
have("aaai_28150")

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

curl https://syntology.ai/api/ran/aaai_28150.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_28150.svg)](https://syntology.ai/paper/aaai_28150)

Connect an agent — have() is free.