SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.12043 · ICLR · 2023

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

Wei Hu, Fan Zhang, Jun Liu, Qihao Zhao, Yangyu Huang

arXiv · PDF · Open in the Atlas

Code that ran

16 of 18 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, 1 violated it and 1 has no contract verdict; 14 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2304.12043.json · badge: /api/ran/2304.12043.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
fistyee/MixPro canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
fistyee/mixpro canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fistyee/MixPro/models/swin_mlp.py
code served (permissive licence) · get_code("144d10b49baeb8a6")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:38:58Z). 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 tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# Using distinct sizes: 2, 8, 8, 4
x = torch.randn(2, 8, 8, 4)

# window_size must divide both H and W evenly
# H=8, W=8, so window_size=4 works (8 // 4 = 2)
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) — shape (8, 4, 4, 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
MaskMix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fistyee/mixpro/utils.py
code served (permissive licence) · get_code("03c58083e2ecf6c7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. 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
import numpy as np

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

# Tiny batch size and dimensions
batch_size = 2
num_classes = 4
mask_num = 2
image_size = 8
channels = 3

# Create sample tensors
samples = torch.randn(batch_size, channels, image_size, image_size)
flip_samples = torch.randn(batch_size, channels, image_size, image_size)

# Create target tensors (class indices)
targets = torch.tensor([0, 2], dtype=torch.long)
flip_targets = torch.tensor([1, 3], dtype=torch.long)

# Parameters for MaskMix
alpha = 1.0
scale_ = 2
scale = 4
label_smoothing = 0.1

ARGS = {
    'samples': samples,
    'flip_samples': flip_samples,
    'alpha': alpha,
    'mask_num': mask_num,
    'scale_': scale_,
    'scale': scale,
    'targets': targets,
    'flip_targets': flip_targets,
    'label_smoothing': label_smoothing,
    'num_classes': num_classes,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
MaskMix Ran
ran on a synthesized input
fistyee/MixPro/utils.py
code served (permissive licence) · get_code("9fc4335dd1dc6864")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. 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
import numpy as np

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

# Construct arguments for MaskMix
batch_size = 2
num_classes = 4
mask_num = 2
image_size = 8
scale_ = 2
scale = 4

# Create sample tensors
samples = torch.randn(batch_size, 3, image_size, image_size)
flip_samples = torch.randn(batch_size, 3, image_size, image_size)

# Create target tensors (class indices)
targets = torch.tensor([0, 1], dtype=torch.long)
flip_targets = torch.tensor([2, 3], dtype=torch.long)

# Other parameters
alpha = 1.0
label_smoothing = 0.1

ARGS = {
    'samples': samples,
    'flip_samples': flip_samples,
    'alpha': alpha,
    'mask_num': mask_num,
    'scale_': scale_,
    'scale': scale,
    'targets': targets,
    'flip_targets': flip_targets,
    'label_smoothing': label_smoothing,
    'num_classes': num_classes,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_optimizer Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from CBalance/SSD, is pointer only (licence: NONE) · get_code("e35a4b2e4114b1a5")
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 CBalance/SSD, 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.

build_scheduler Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/lr_scheduler.py
pointer only (licence: MIT); the stored copy get_code serves, from ghrua/seqpe, is pointer only (licence: NONE) · get_code("c02cc4e0b5720211")
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 ghrua/seqpe, 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.

check_keywords_in_name Ran
ran, violated the contract we drafted
fistyee/MixPro/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("b0a5beb34716d5a6")
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 leaplabthu/inline, 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.

checkpoint_filter_fn Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/models/vit.py
pointer only (licence: MIT); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("5dac11fdc41c896b")
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 leaplabthu/inline, 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.

create_logger Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/logger.py
pointer only (licence: MIT); the stored copy get_code serves, from ghrua/seqpe, is pointer only (licence: NONE) · get_code("80450600f7f09b0a")
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 ghrua/seqpe, 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.

mixup_target Ran
ran; our contract draft was wrong, not the code
fistyee/mixpro/utils.py
code served (permissive licence) · get_code("08b4e547f3100fc0")
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, 5) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for target and old_target
# These should be 1D tensors of class indices
target = torch.tensor([0, 2, 1, 3], dtype=torch.long)
old_target = torch.tensor([1, 0, 3, 2], dtype=torch.long)

# Parameters for mixup_target
num_classes = 5
lam = 0.7
smoothing = 0.1
device = 'cpu'

ARGS = {
    'target': target,
    'old_target': old_target,
    'num_classes': num_classes,
    'lam': lam,
    'smoothing': smoothing,
    'device': device
}
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 (4, 5) — shape (4, 5) 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
one_hot Ran
ran; our contract draft was wrong, not the code
fistyee/mixpro/utils.py
code served (permissive licence) · get_code("4728dc2025227bba")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small input tensor with class indices
# Shape: (2,) - batch of 2 samples with class indices
x = torch.tensor([0, 2], dtype=torch.long)

# Number of classes
num_classes = 4

# On value for one-hot encoding
on_value = 1.0

# Off value for one-hot encoding
off_value = 0.0

# Device - use CPU only
device = 'cpu'

ARGS = {
    'x': x,
    'num_classes': num_classes,
    'on_value': on_value,
    'off_value': off_value,
    'device': device
}
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
resize_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fistyee/MixPro/models/vit.py
pointer only (licence: MIT); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("1dbef2d4da4ee10f")
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 leaplabthu/inline, 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.

set_weight_decay Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from ztx-100/efficient_vit_with_dw, is pointer only (licence: NONE) · get_code("b33222a09fc93bec")
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 ztx-100/efficient_vit_with_dw, 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.

window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fistyee/MixPro/models/focal_transformer_v2.py
code served (permissive licence) · get_code("f9fd6241d935f07b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (12, 4, 4, 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

torch.manual_seed(0)

# Create a tensor with shape (B, H, W, C)
# B = 2 (batch size)
# H = 8 (height, must be divisible by window_size)
# W = 12 (width, must be divisible by window_size)
# C = 4 (channels)
# window_size = 4

B = 2
H = 8
W = 12
C = 4
window_size = 4

x = torch.randn(B, H, W, C)

ARGS = {
    'x': x,
    'window_size': window_size
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (12, 4, 4, 4) — shape (12, 4, 4, 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
window_partition_noreshape Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fistyee/MixPro/models/focal_transformer_v2.py
pointer only (licence: MIT); the stored copy get_code serves, from felix-schmitt/MathNet, is pointer only (licence: CC-BY-4.0) · get_code("eb8623dc7c37757f")
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 felix-schmitt/MathNet, and CC-BY-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

window_reverse Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/models/swin_mlp.py
code served (permissive licence) · get_code("61bf152e6a42a184")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 12, 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)

# Parameters for window_reverse
# windows: (num_windows*B, window_size, window_size, C)
# The function expects windows to be partitioned from an image of size (B, H, W, C)
# where the image is divided into non-overlapping windows of size window_size x window_size

B = 2  # batch size
H = 8  # image height
W = 12  # image width
window_size = 4  # window size
C = 3  # number of channels

# Calculate number of windows
num_windows_h = H // window_size  # 2
num_windows_w = W // window_size  # 3
num_windows = num_windows_h * num_windows_w  # 6

# windows shape: (num_windows*B, window_size, window_size, C)
# = (6*2, 4, 4, 3) = (12, 4, 4, 3)
windows = torch.randn(num_windows * B, window_size, window_size, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 8, 12, 3) — shape (2, 8, 12, 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
window_reverse Ran
ran; our contract draft was wrong, not the code
fistyee/MixPro/models/focal_transformer_v2.py
code served (permissive licence) · get_code("fb32094c6dbece71")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 12, 6) 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)

# Define parameters
# We need windows of shape (num_windows*B, window_size, window_size, C)
# where num_windows = (H // window_size) * (W // window_size)

B = 2
H = 8
W = 12
window_size = 4
C = 6

# Calculate num_windows
num_windows_h = H // window_size  # 8 // 4 = 2
num_windows_w = W // window_size  # 12 // 4 = 3
num_windows = num_windows_h * num_windows_w  # 2 * 3 = 6

# Total number of windows across batch
total_windows = num_windows * B  # 6 * 2 = 12

# Create windows tensor
windows = torch.randn(total_windows, window_size, window_size, C)

ARGS = {
    'windows': windows,
    'window_size': window_size,
    'H': H,
    'W': W
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 8, 12, 6) — shape (2, 8, 12, 6) 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
build_model Not yet run
unverified (harvested, no recorded run)
fistyee/MixPro/models/build.py
code served (permissive licence) · get_code("1ecb57de91ce4988")
How it ran

no invocation recorded.

get_config Not yet run
unverified (harvested, no recorded run)
fistyee/MixPro/config.py
code served (permissive licence) · get_code("9b9b6364be5f95f6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 2 the same month, 12 later) and 3 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
window_reverse 227 other papers
87 dated earlier, 2 the same month, 129 later, 9 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
81 dated earlier, 2 the same month, 131 later, 9 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
get_config 51 other papers
16 dated earlier, 32 later, 3 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 48 more not named here
checkpoint_filter_fn 37 other papers
11 dated earlier, 23 later, 3 same year, order not determinable · 1 only as an assembly brick
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2112.07658 (2021-12)
AdaViT: Adaptive Tokens for Efficient Vision Transformer
and 34 more not named here
create_logger 35 other papers
13 dated earlier, 20 later, 2 same year, order not determinable
2104.13840 (2021-04)
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 32 more not named here
check_keywords_in_name 31 other papers
10 dated earlier, 20 later, 1 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 28 more not named here
resize_pos_embed 14 other papers
7 dated earlier, 7 later
2112.07658 (2021-12)
AdaViT: Adaptive Tokens for Efficient Vision Transformer
2203.05962 (2022-03)
Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice
2203.12614 (2022-03)
Unsupervised Salient Object Detection with Spectral Cluster Voting
and 11 more not named here
set_weight_decay 14 other papers
6 dated earlier, 8 later
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 11 more not named here
build_scheduler 13 other papers
9 dated earlier, 3 later, 1 same year, order not determinable
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
2106.04263 (2021-06)
On the Connection between Local Attention and Dynamic Depth-wise Convolution
and 10 more not named here
one_hot
brick of this paper's assembly: helper
12 other papers
5 dated earlier, 7 later · 1 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2212.00776 (2022-12)
ResFormer: Scaling ViTs with Multi-Resolution Training
and 9 more not named here
build_optimizer 8 other papers
5 dated earlier, 3 later
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
2106.04263 (2021-06)
On the Connection between Local Attention and Dynamic Depth-wise Convolution
and 5 more not named here
window_partition_noreshape 2 other papers
1 dated earlier, 1 later
2210.14319 (2022-10)
Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets
2404.13667 (2024-04)
MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition

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

The recently proposed data augmentation TransMix employs attention labels to help visual transformers (ViT) achieve better robustness and performance. However, TransMix is deficient in two aspects: 1) The image cropping method of TransMix may not be suitable for ViTs. 2) At the early stage of training, the model produces unreliable attention maps. TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model. To address the aforementioned issues, we propose MaskMix and Progressive Attention Labeling (PAL) in image and label space, respectively. In detail, from the perspective of image space, we design MaskMix, which mixes two images based on a patch-like grid mask. In particular, the size of each mask patch is adjustable and is a multiple of the image patch size, which ensures each image patch comes from only one image and contains more global contents. From the perspective of label space, we design PAL, which utilizes a progressive factor to dynamically re-weight the attention weights of the mixed attention label. Finally, we combine MaskMix and Progressive Attention Labeling as our new data augmentation method, named MixPro. The experimental results show that our method can improve various ViT-based models at scales on ImageNet classification (73.8% top-1 accuracy based on DeiT-T for 300 epochs). After being pre-trained with MixPro on ImageNet, the ViT-based models also demonstrate better transferability to semantic segmentation, object detection, and instance segmentation. Furthermore, compared to TransMix, MixPro also shows stronger robustness on several benchmarks. The code is available at https://github.com/fistyee/MixPro.

For agents

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

get_harvested_code_for_paper("2304.12043")
get_code_for_paper("2304.12043")
have("2304.12043")

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

curl https://syntology.ai/api/ran/2304.12043.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.12043.svg)](https://syntology.ai/paper/2304.12043)

Connect an agent — have() is free.