SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.03036 · ECCV · 2022

Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space

Yixiao Ge, Wenqi Shao, Ping Luo, Xiaogang Wang, Zhaoyang Zhang, Ying Shan, Lei Yang, Xun Zhao

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 0 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/2207.03036.json · badge: /api/ran/2207.03036.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
TencentARC/SFDA community
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
SFDA Ran
ran on a synthesized input · constructed an object; no result was computed
TencentARC/SFDA/metrics.py
pointer only (licence: NONE) · get_code("e957435048528920")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TencentARC/SFDA 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.

_cov Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TencentARC/SFDA/metrics.py
pointer only (licence: NONE) · get_code("fc681a5a125b783a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TencentARC/SFDA 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.

iterative_A Ran
ran; our contract draft was wrong, not the code
TencentARC/SFDA/metrics.py
pointer only (licence: NONE) · get_code("a4dfd56760474768")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TencentARC/SFDA 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.

softmax Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TencentARC/SFDA/metrics.py
pointer only (licence: NONE) · get_code("a8ae5c6e4eb58226")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TencentARC/SFDA 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 0 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
SFDA
brick of this paper's assembly: entry
1 other paper
1 later · 1 only as an assembly brick
2308.15074 (2023-08)
Exploring Model Transferability through the Lens of Potential Energy
_cov
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2308.15074 (2023-08)
Exploring Model Transferability through the Lens of Potential Energy
iterative_A
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2308.15074 (2023-08)
Exploring Model Transferability through the Lens of Potential Energy
softmax
brick of this paper's assembly: helper
1 other paper
1 later
2308.15074 (2023-08)
Exploring Model Transferability through the Lens of Potential Energy

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

This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pretrained models on the target dataset, which is brute-force and computationally expensive. Recent advanced methods proposed several lightweight transferability metrics to predict the fine-tuning results. However, these approaches only capture static representations but neglect the fine-tuning dynamics. To this end, this paper proposes a new transferability metric, called Self-challenging Fisher Discriminant Analysis (SFDA), which has many appealing benefits that existing works do not have. First, SFDA can embed the static features into a Fisher space and refine them for better separability between classes. Second, SFDA uses a selfchallenging mechanism to encourage different pre-trained models to differentiate on hard examples. Third, SFDA can easily select multiple pre-trained models for the model ensemble. Extensive experiments on 33 pre-trained models of 11 downstream tasks show that SFDA is efficient, effective, and robust when measuring the transferability of pretrained models. For instance, compared with the state-of-the-art method NLEEP, SFDA demonstrates an average of 59.1% gain while bringing 22.5x speedup in wall-clock time. The code will be available at https://github.com/TencentARC/SFDA.

For agents

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

get_harvested_code_for_paper("2207.03036")
get_code_for_paper("2207.03036")
have("2207.03036")

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

curl https://syntology.ai/api/ran/2207.03036.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.03036.svg)](https://syntology.ai/paper/2207.03036)

Connect an agent — have() is free.