SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13890 · 2020

Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

arXiv · PDF · Open in the Atlas

Code that ran

11 of 19 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 5 have no contract verdict; 6 failures of our instrument; 8 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/2007.13890.json · badge: /api/ran/2007.13890.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
djidje/D-MMD canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
fremigereau/mtda_kd_reid community (classifier label)
classifier basis not recorded on the link
3 ran · 6 no recorded run
FunctionStatusWhere it lives
adjoint Ran
ran on a synthesized input
fremigereau/mtda_kd_reid/torchreid/losses/log_euclid_loss.py
code served (permissive licence) · get_code("a8784aa9b1f9f43d")
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, 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)

# A: complex matrix (n x n)
n = 4
A = torch.randn(n, n, dtype=torch.complex64)

# E: matrix (n x n), will be used in M construction and determine dtype/device
E = torch.randn(n, n, dtype=torch.float32)

# f: callable that takes a matrix and returns a matrix
# Looking at the function body, f(M) is called where M is (2n x 2n)
# and the result is indexed with [:n, n:], so f should return a (2n x 2n) matrix
def f(M):
    # Simple identity-like operation: just return the input
    return M

ARGS = {
    "A": A,
    "E": E,
    "f": f,
}
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, 4) — shape (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
compute_distance_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
djidje/D-MMD/torchreid/metrics/distance.py
code served (permissive licence) · get_code("47abff66686e1367")
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, 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small 2-D feature tensors
# input1: 2 samples, 4 features
input1 = torch.rand(2, 4)

# input2: 3 samples, 4 features
input2 = torch.rand(3, 4)

# metric parameter
metric = 'euclidean'

ARGS = {
    'input1': input1,
    'input2': input2,
    'metric': metric
}
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, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv1x1 Ran
ran; our contract draft was wrong, not the code
djidje/D-MMD/torchreid/models/resnet.py
code served (permissive licence) · get_code("158bf4c3a5f11f04")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
djidje/D-MMD/torchreid/models/resnet.py
code served (permissive licence) · get_code("29df79c9fdb0cee8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
cosine_distance Ran
ran on a synthesized input
djidje/D-MMD/torchreid/metrics/distance.py
code served (permissive licence) · get_code("e8878931ade705ee")
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, 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 torch.nn as nn
from torch.nn import functional as F

torch.manual_seed(0)

# Create two 2-D feature matrices with distinct sizes
# input1: batch_size=2, feature_dim=4
# input2: batch_size=3, feature_dim=4
input1 = torch.randn(2, 4)
input2 = torch.randn(3, 4)

ARGS = {
    "input1": input1,
    "input2": input2,
}
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, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
euclidean_squared_distance Ran
ran on a synthesized input
djidje/D-MMD/torchreid/metrics/distance.py
code served (permissive licence) · get_code("7f07c9c709558f20")
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, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create two 2-D feature matrices with distinct sizes
# input1: 2 samples, 4 features
# input2: 3 samples, 4 features
input1 = torch.randn(2, 4)
input2 = torch.randn(3, 4)

ARGS = {
    "input1": input1,
    "input2": input2,
}
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, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
hook_convNd Ran
ran; our contract draft was wrong, not the code
djidje/D-MMD/torchreid/utils/model_complexity.py
pointer only (licence: MIT); the stored copy get_code serves, from zhoujiahuan1991/ICCV2025-SPRED, is pointer only (licence: NONE) · get_code("864af8714b01d899")
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 zhoujiahuan1991/ICCV2025-SPRED, 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.

hook_maxpool1d Ran
ran; our contract draft was wrong, not the code
djidje/D-MMD/torchreid/utils/model_complexity.py
pointer only (licence: MIT); the stored copy get_code serves, from zhoujiahuan1991/ICCV2025-SPRED, is pointer only (licence: NONE) · get_code("3da6ed703abc90f2")
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 zhoujiahuan1991/ICCV2025-SPRED, 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.

hook_maxpool2d Ran
ran; our contract draft was wrong, not the code
djidje/D-MMD/torchreid/utils/model_complexity.py
pointer only (licence: MIT); the stored copy get_code serves, from zhoujiahuan1991/ICCV2025-SPRED, is pointer only (licence: NONE) · get_code("ac37e89d43b7c73b")
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 zhoujiahuan1991/ICCV2025-SPRED, 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.

logm Ran
ran on a synthesized input
fremigereau/mtda_kd_reid/torchreid/losses/log_euclid_loss.py
code served (permissive licence) · get_code("ad3e59b7ac358ac0")
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, 2) 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 scipy.linalg

torch.manual_seed(0)

# Create a small square matrix for logm computation
# The matrix should be invertible and have a well-defined matrix logarithm
# Using a simple positive definite matrix
A = torch.tensor([[2.0, 0.5], [0.5, 2.0]], dtype=torch.float32)

ARGS = {
    "x": A
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
scipy, 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, 2) — shape (2, 2) 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
logm_scipy Ran
ran on a synthesized input
fremigereau/mtda_kd_reid/torchreid/losses/log_euclid_loss.py
code served (permissive licence) · get_code("a3c2efa887b61229")
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, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import scipy.linalg

torch.manual_seed(0)

# The function expects a tensor A that:
# - Has a .cpu() method (it's a torch tensor)
# - Has a .device attribute
# - Can be converted from numpy back to torch
# - Should be a square matrix for scipy.linalg.logm

# Create a small square matrix tensor on CPU
# Using a positive definite matrix to ensure logm is well-defined
A = torch.tensor([
    [2.0, 0.5],
    [0.5, 2.0]
], dtype=torch.complex64)

ARGS = {
    "A": A
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, 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, 2) — shape (2, 2) 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
accuracy Not yet run
unverified (harvested, no recorded run)
djidje/D-MMD/torchreid/metrics/accuracy.py
code served (permissive licence) · get_code("3f035a8f26b7201e")
How it ran

no invocation recorded.

init_pretrained_weights Not yet run
unverified (harvested, no recorded run)
fremigereau/mtda_kd_reid/torchreid/models/osnet.py
code served (permissive licence) · get_code("64a159f6f4dbec43")
How it ran

no invocation recorded.

mobilenetv2_x1_0 Not yet run
unverified (harvested, no recorded run)
fremigereau/mtda_kd_reid/torchreid/models/mobilenetv2.py
code served (permissive licence) · get_code("a3b2dfaeb8242a74")
How it ran

no invocation recorded.

mobilenetv2_x1_4 Not yet run
unverified (harvested, no recorded run)
fremigereau/mtda_kd_reid/torchreid/models/mobilenetv2.py
code served (permissive licence) · get_code("85fe509123aeb62c")
How it ran

no invocation recorded.

osnet_x0_75 Not yet run
unverified (harvested, no recorded run)
fremigereau/mtda_kd_reid/torchreid/models/osnet.py
code served (permissive licence) · get_code("e16bb8aa7f328ab6")
How it ran

no invocation recorded.

osnet_x1_0 Not yet run
unverified (harvested, no recorded run)
fremigereau/mtda_kd_reid/torchreid/models/osnet.py
code served (permissive licence) · get_code("33e115bbbea25b98")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
fremigereau/mtda_kd_reid/torchreid/models/resnet.py
code served (permissive licence) · get_code("d0707f6bcff796e4")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
djidje/D-MMD/torchreid/models/resnet.py
code served (permissive licence) · get_code("1b930b1d1d88f2b9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 8 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
83 dated earlier, 9 the same month, 338 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
43 dated earlier, 5 the same month, 263 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
init_pretrained_weights 4 other papers
3 dated earlier, 1 later
1905.00953 (2019-05)
Omni-Scale Feature Learning for Person Re-Identification
1910.06827 (2019-10)
Learning Generalisable Omni-Scale Representations for Person Re-Identification
1910.10093 (2019-10)
Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
and 1 more not named here
compute_distance_matrix 2 other papers
1 dated earlier, 1 later
1710.03077 (2017-10)
Deeper, Broader and Artier Domain Generalization
2210.04206 (2022-10)
Attention Diversification for Domain Generalization
cosine_distance 2 other papers
1 dated earlier, 1 later
1710.03077 (2017-10)
Deeper, Broader and Artier Domain Generalization
2210.04206 (2022-10)
Attention Diversification for Domain Generalization
hook_convNd 2 other papers
2 later
Xu_Distribution-aware_Knowledge_Prototyping_for_Non-exemplar_Lifelong_Person_Re-identification_CVPR_2024_paper (2024 (year only))
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
2507.01884 (2025-07)
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
hook_maxpool1d 2 other papers
2 later
Xu_Distribution-aware_Knowledge_Prototyping_for_Non-exemplar_Lifelong_Person_Re-identification_CVPR_2024_paper (2024 (year only))
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
2507.01884 (2025-07)
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
hook_maxpool2d 2 other papers
2 later
Xu_Distribution-aware_Knowledge_Prototyping_for_Non-exemplar_Lifelong_Person_Re-identification_CVPR_2024_paper (2024 (year only))
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
2507.01884 (2025-07)
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
accuracy 1 other paper
1 dated earlier
1908.01114 (2019-08)
ABD-Net: Attentive but Diverse Person Re-Identification

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

Person re-identification (ReID) remains a challenging task in many real-word video analytics and surveillance applications, even though state-of-the-art accuracy has improved considerably with the advent of deep learning (DL) models trained on large image datasets. Given the shift in distributions that typically occurs between video data captured from the source and target domains, and absence of labeled data from the target domain, it is difficult to adapt a DL model for accurate recognition of target data. We argue that for pair-wise matchers that rely on metric learning, e.g., Siamese networks for person ReID, the unsupervised domain adaptation (UDA) objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations. Moreover, dissimilarity representations are more suitable for designing open-set ReID systems, where identities differ in the source and target domains. In this paper, we propose a novel Dissimilarity-based Maximum Mean Discrepancy (D-MMD) loss for aligning pair-wise distances that can be optimized via gradient descent. From a person ReID perspective, the evaluation of D-MMD loss is straightforward since the tracklet information allows to label a distance vector as being either within-class or between-class. This allows approximating the underlying distribution of target pair-wise distances for D-MMD loss optimization, and accordingly align source and target distance distributions. Empirical results with three challenging benchmark datasets show that the proposed D-MMD loss decreases as source and domain distributions become more similar. Extensive experimental evaluation also indicates that UDA methods that rely on the D-MMD loss can significantly outperform baseline and state-of-the-art UDA methods for person ReID without the common requirement for data augmentation and/or complex networks.

For agents

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

get_harvested_code_for_paper("2007.13890")
get_code_for_paper("2007.13890")
have("2007.13890")

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

curl https://syntology.ai/api/ran/2007.13890.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13890.svg)](https://syntology.ai/paper/2007.13890)

Connect an agent — have() is free.