SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.02713 · NeurIPS · 2020

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Yixiao Ge, Dapeng Chen, Hongsheng Li, Feng Zhu, Rui Zhao

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 2 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/2006.02713.json · badge: /api/ran/2006.02713.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
yxgeee/SpCL marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
open-mmlab/OpenUnReID community
Papers with Code archive
0 ran · 2 no recorded run
FunctionStatusWhere it lives
HM Ran
ran on a synthesized input · constructed an object; no result was computed
yxgeee/SpCL/spcl/models/hm.py
code served (permissive licence) · get_code("198515d7a87b4074")
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, HM: 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 torch
from torch import nn, autograd

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# inputs: batch_size=2, feature_dim=4
inputs = torch.randn(2, 4)

# indexes: indices into features, batch_size=2
indexes = torch.tensor([0, 1])

# features: num_classes=3, feature_dim=4
features = torch.randn(3, 4)
# Normalize features as expected by the backward pass
features = features / features.norm(dim=1, keepdim=True)

# momentum: scalar value for exponential moving average
momentum = 0.9

ARGS = {
    'inputs': inputs,
    'indexes': indexes,
    'features': features,
    'momentum': momentum
}
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 HM — 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 HM 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
HybridMemory Ran
ran on a synthesized input · constructed an object; no result was computed
yxgeee/SpCL/spcl/models/hm.py
code served (permissive licence) · get_code("94a0cbacdd9fae2e")
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, HybridMemory: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The HybridMemory module needs:
# - num_features: dimension of feature vectors
# - num_samples: total number of samples in memory
# - temp: temperature parameter (default 0.05)
# - momentum: momentum parameter (default 0.2)

# Looking at the forward method:
# - inputs: tensor of shape (B, num_features) where B is batch size
# - indexes: tensor of shape (B,) with indices into the memory
# - The module uses self.features (num_samples, num_features) and self.labels (num_samples,)
# - forward() calls hm() which does matrix multiply and updates features
# - It computes similarities and uses self.labels to create masks

num_features = 4
num_samples = 8
batch_size = 2

# Initialize the module
model = nn.Module()  # placeholder

# For testing, we need to set up the HybridMemory instance
# but we're asked to provide ARGS for the constructor parameters

ARGS = {
    'num_features': 4,
    'num_samples': 8,
    'temp': 0.05,
    'momentum': 0.2
}
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 HybridMemory — 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 HybridMemory 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
hm Ran
ran; our contract draft was wrong, not the code
yxgeee/SpCL/spcl/models/hm.py
code served (permissive licence) · get_code("6bee8a7a58df869e")
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
from torch import nn, autograd

torch.manual_seed(0)

# Construct tensors with distinct sizes
# inputs: (batch_size=2, feature_dim=4)
inputs = torch.randn(2, 4)

# indexes: indices into features tensor, shape (2,)
indexes = torch.tensor([0, 1], dtype=torch.long)

# features: (num_classes=3, feature_dim=4) - distinct from inputs batch size
features = torch.randn(3, 4)

# momentum: scalar value
momentum = 0.5

ARGS = {
    "inputs": inputs,
    "indexes": indexes,
    "features": features,
    "momentum": momentum,
}
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
HybridMemory Not yet run
unverified (harvested, no recorded run)
open-mmlab/OpenUnReID/openunreid/models/losses/memory.py
code served (permissive licence) · get_code("21c9ef17b1caacd1")
How it ran

no invocation recorded.

hm Not yet run
unverified (harvested, no recorded run)
open-mmlab/OpenUnReID/openunreid/models/losses/memory.py
code served (permissive licence) · get_code("669dde59f08f64b3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods [11,54,10,55,14] have achieved great success, they did not make full use of all valuable information because of the domain gap and unsatisfying clustering performance. To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory. The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clustered instance-level supervisory signals for learning feature representations. Different from the conventional contrastive learning strategy, the proposed framework jointly distinguishes source-domain classes, and target-domain clusters and un-clustered instances. Most importantly, the proposed self-paced method gradually creates more reliable clusters to refine the hybrid memory and learning targets, and is shown to be the key to our outstanding performance. Our method outperforms state-ofthe-arts on multiple domain adaptation tasks of object re-ID and even boosts the performance on the source domain without any extra annotations. Our generalized version on unsupervised object re-ID surpasses state-of-the-art algorithms by considerable 16.7% and 7.9% on Market-1501 and MSMT17 benchmarks † .

For agents

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

get_harvested_code_for_paper("2006.02713")
get_code_for_paper("2006.02713")
have("2006.02713")

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

curl https://syntology.ai/api/ran/2006.02713.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.02713.svg)](https://syntology.ai/paper/2006.02713)

Connect an agent — have() is free.