SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.03421 · CVPR · 2024

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

Guang Chen, Alois Knoll, Sanqing Qu, Changjun Jiang, Lianghua He, Tianpei Zou, Florian Röhrbein

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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 0 have no contract verdict; 9 failures 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/2403.03421.json · badge: /api/ran/2403.03421.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
ispc-lab/glc canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
ispc-lab/lead canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
Entropy Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/utils/net_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from albert0147/aad_sfda, is pointer only (licence: NONE) · get_code("94b5622f0aa7add1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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.

log_args Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/utils/net_utils.py
pointer only (licence: NONE) · get_code("a7928c7cf111366a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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.

lr_scheduler Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/train_source.py
pointer only (licence: NONE); the stored copy get_code serves, from albert0147/aad_sfda, is pointer only (licence: NONE) · get_code("0b7ffc9f8b77529c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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.

op_copy Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/train_source.py
pointer only (licence: NONE); the stored copy get_code serves, from albert0147/aad_sfda, is pointer only (licence: NONE) · get_code("93a11f62e4a129f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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_logger Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/utils/net_utils.py
pointer only (licence: NONE) · get_code("59fb5d13731e4308")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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_logger Ran
ran; our contract draft was wrong, not the code
ispc-lab/lead/utils/net_utils.py
code served (permissive licence) · get_code("218cf492f8713f71")
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 Logger. 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 os
import sys
import logging
import tempfile

class Args:
    def __init__(self):
        self.test = False
        self.save_dir = tempfile.gettempdir()
        self.model_name = "test_model"
        self.learning_rate = 0.001
        self.batch_size = 32
        self.epochs = 10

args = Args()

ARGS = {
    'args': args,
    'log_name': 'train_log.txt'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
test_transform Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/dataset/dataset.py
pointer only (licence: NONE) · get_code("13b7b1c692c187e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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.

train Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ispc-lab/glc/train_source.py
pointer only (licence: NONE) · get_code("e4b2648a312cebb6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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.

train_transform Ran
ran; our contract draft was wrong, not the code
ispc-lab/glc/dataset/dataset.py
pointer only (licence: NONE) · get_code("ada9656c14c75934")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc 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.

obtain_LEAD_pseudo_labels Not yet run
unverified (harvested, no recorded run)
ispc-lab/lead/train_target.py
code served (permissive licence) · get_code("f64aa135fdd5f173")
How it ran

no invocation recorded.

obtain_global_pseudo_labels Not yet run
unverified (harvested, no recorded run)
ispc-lab/glc/train_target.py
pointer only (licence: NONE) · get_code("5b48697e26a31d82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispc-lab/glc when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 8 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
op_copy 21 other papers
15 dated earlier, 1 the same month, 5 later · 5 only as an assembly brick
2002.08546 (2020-02)
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
2012.07297 (2020-12)
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
2104.01539 (2021-04)
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
and 18 more not named here
lr_scheduler 18 other papers
13 dated earlier, 1 the same month, 4 later · 3 only as an assembly brick
2002.08546 (2020-02)
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
2012.07297 (2020-12)
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
2104.01539 (2021-04)
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
and 15 more not named here
Entropy 16 other papers
13 dated earlier, 1 the same month, 2 later · 4 only as an assembly brick
2007.14612 (2020-07)
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
2104.01539 (2021-04)
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
2104.01845 (2021-04)
Unsupervised Multi-source Domain Adaptation Without Access to Source Data
and 13 more not named here
log_args 1 other paper
1 later
2607.17653 (2026-07)
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
set_logger 1 other paper
1 later
2607.17653 (2026-07)
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
test_transform 1 other paper
1 later
2607.17653 (2026-07)
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
train 1 other paper
1 later
2411.12558 (2024-11)
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework
train_transform 1 other paper
1 later
2607.17653 (2026-07)
LFM: Leveraging Foundation Models for Source-Free Universal 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

Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data, which tends to be more practical due to data protection policies. The main challenge lies in determining whether covariate-shifted samples belong to target-private unknown categories. Existing methods tackle this either through hand-crafted thresholding or by developing time-consuming iterative clustering strategies. In this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify targetprivate data. Technically, LEAD initially leverages the orthogonal decomposition analysis for feature decomposition. Then, LEAD builds instance-level decision boundaries to adaptively identify target-private data. Extensive experiments across various UniDA scenarios have demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA scenario on VisDA dataset, LEAD outperforms GLC by 3.5% overall H-score and reduces 75% time to derive pseudo-labeling decision boundaries. Besides, LEAD is also appealing in that it is complementary to most existing methods. The code is available at https://github. com/ispc-lab/LEAD.

For agents

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

get_harvested_code_for_paper("2403.03421")
get_code_for_paper("2403.03421")
have("2403.03421")

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

curl https://syntology.ai/api/ran/2403.03421.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.03421.svg)](https://syntology.ai/paper/2403.03421)

Connect an agent — have() is free.