SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.08823 · 2022

Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 3 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/2210.08823.json · badge: /api/ran/2210.08823.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
dongzelian/ssf canonical (classifier label)
classifier basis not recorded on the link
12 ran · 3 no recorded run
FunctionStatusWhere it lives
MyNorm Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/models/as_mlp.py
pointer only (licence: MIT); the stored copy get_code serves, from ggjy/Hire-Wave-MLP.pytorch, is pointer only (licence: NONE) · get_code("c3f4c265067c1717")
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 ggjy/Hire-Wave-MLP.pytorch, 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.

get_init_weights_vit Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/models/vision_transformer.py
code served (permissive licence) · get_code("def23f7d7d042968")
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 partial. 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
from functools import partial

torch.manual_seed(0)

# Create a minimal test module with the structure that get_init_weights_vit expects
class SimpleViTModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.head = nn.Linear(4, 2)
        self.qkv = nn.Linear(4, 12)
        self.mlp_layer = nn.Linear(4, 3)
    
    def forward(self, x):
        return x

# Test various modes of get_init_weights_vit
ARGS = {
    'mode': 'jax',
    'head_bias': 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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
get_mce_from_accuracy Ran
ran, honoured the contract we drafted
dongzelian/ssf/utils/mce_utils.py
code served (permissive licence) · get_code("a9e48df75d2e823e")
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 float, ndim 0, dtype family float, shape () 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)

# The function get_mce_from_accuracy takes two parameters:
# - accuracy: a numeric value representing accuracy (0-100 scale based on the computation)
# - error_alexnet: a numeric value representing AlexNet error rate

# Looking at the function body:
# - accuracy is used in arithmetic: 100.0 - accuracy
# - error_alexnet is used in arithmetic: error / (error_alexnet * 100.0)
# Both are simple numeric values

ARGS = {
    "accuracy": 85.5,
    "error_alexnet": 0.45
}
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 float, ndim 0, dtype family float, shape () — shape () 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
init_ssf_scale_shift Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/models/vision_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("896b5eec245f1bab")
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 yewen1486/emtal, 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.

init_ssf_scale_shift Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/models/as_mlp.py
code served (permissive licence) · get_code("9873773b10315cc0")
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. 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 function init_ssf_scale_shift takes a single parameter: dim (an integer)
# It creates scale and shift parameters with that dimension
# We'll use a small dimension value

ARGS = {
    "dim": 4
}
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 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
param_groups_weight_decay Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/optim_factory.py
pointer only (licence: MIT); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("88f4962784e09b88")
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 yewen1486/emtal, 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.

resize_pos_embed Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/utils/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from daviddaiiiii/san-peft, is pointer only (licence: NONE) · get_code("6957ddf9520c3d71")
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 daviddaiiiii/san-peft, 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.

resize_pos_embed_cait Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/utils/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from daviddaiiiii/san-peft, is pointer only (licence: NONE) · get_code("0eae5b409f8d3a5b")
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 daviddaiiiii/san-peft, 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.

resize_pos_embed_nocls Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/utils/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from daviddaiiiii/san-peft, is pointer only (licence: NONE) · get_code("f553c9b260a0e6e3")
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 daviddaiiiii/san-peft, 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.

ssf_ada Ran
ran, honoured the contract we drafted
dongzelian/ssf/models/as_mlp.py
pointer only (licence: MIT); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("61e8364b7e9bcb70")
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 yewen1486/emtal, 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)
dongzelian/ssf/models/swin_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from heekhero/DTL, is pointer only (licence: NONE) · get_code("993ae96666b00cb5")
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 heekhero/DTL, 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_reverse Ran
ran; our contract draft was wrong, not the code
dongzelian/ssf/models/swin_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from heekhero/DTL, is pointer only (licence: NONE) · get_code("609922bd93c75117")
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 heekhero/DTL, 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 Not yet run
unverified (harvested, no recorded run)
dongzelian/ssf/models/convnext.py
code served (permissive licence) · get_code("7619bf7f57c5d2b6")
How it ran

no invocation recorded.

group_parameters Not yet run
unverified (harvested, no recorded run)
dongzelian/ssf/optim_factory.py
pointer only (licence: MIT); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("efeb37d90ba28266")
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 yewen1486/emtal, 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. No invocation recorded.

group_with_matcher Not yet run
unverified (harvested, no recorded run)
dongzelian/ssf/optim_factory.py
pointer only (licence: MIT); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("0332519996466b5a")
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 yewen1486/emtal, 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 14 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 14 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
window_partition 31 other papers
3 dated earlier, 1 the same month, 27 later
2111.11418 (2021-11)
MetaFormer Is Actually What You Need for Vision
2203.12119 (2022-03)
Visual Prompt Tuning
2204.03645 (2022-04)
DaViT: Dual Attention Vision Transformers
and 28 more not named here
get_init_weights_vit 25 other papers
2 dated earlier, 23 later · 1 only as an assembly brick
2112.08654 (2021-12)
Learning to Prompt for Continual Learning
2207.12819 (2022-07)
S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
aaai_26216 (2023 (year only))
Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference
and 22 more not named here
param_groups_weight_decay 15 other papers
15 later
2304.14065 (2023-04)
Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
2305.13002 (2023-05)
Rethinking Semi-supervised Learning with Language Models
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
and 12 more not named here
ssf_ada 8 other papers
8 later · 1 only as an assembly brick
2307.02251 (2023-07)
RanPAC: Random Projections and Pre-trained Models for Continual Learning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2312.08888 (2023-12)
Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models
and 5 more not named here
init_ssf_scale_shift 7 other papers
7 later
2307.02251 (2023-07)
RanPAC: Random Projections and Pre-trained Models for Continual Learning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2312.08888 (2023-12)
Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models
and 4 more not named here
group_parameters 6 other papers
6 later
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2308.13168 (2023-08)
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
2312.10136 (2023-12)
Gradient-based Parameter Selection for Efficient Fine-Tuning
and 3 more not named here
window_reverse 6 other papers
1 dated earlier, 5 later
2203.12119 (2022-03)
Visual Prompt Tuning
Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper (2023 (year only))
Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
and 3 more not named here
MyNorm 4 other papers
2 dated earlier, 2 later
2107.08391 (2021-07)
AS-MLP: An Axial Shifted MLP Architecture for Vision
2108.13341 (2021-08)
Hire-MLP: Vision MLP via Hierarchical Rearrangement
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
and 1 more not named here
get_mce_from_accuracy 4 other papers
4 later
Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper (2023 (year only))
Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2310.12973 (2023-10)
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
and 1 more not named here
group_with_matcher 4 other papers
4 later
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2312.10136 (2023-12)
Gradient-based Parameter Selection for Efficient Fine-Tuning
2409.06706 (2024-09)
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
and 1 more not named here
checkpoint_filter_fn 3 other papers
3 later
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2312.10136 (2023-12)
Gradient-based Parameter Selection for Efficient Fine-Tuning
2411.01800 (2024-11)
Expanding Sparse Tuning for Low Memory Usage
resize_pos_embed 3 other papers
2 dated earlier, 1 later
2106.12368 (2021-06)
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
2208.01313 (2022-08)
Unified Normalization for Accelerating and Stabilizing Transformers
2409.06706 (2024-09)
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
resize_pos_embed_cait 1 other paper
1 later
2409.06706 (2024-09)
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
resize_pos_embed_nocls 1 other paper
1 later
2409.06706 (2024-09)
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning

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

Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full fine-tuning. In this paper, we propose a new parameter-efficient fine-tuning method termed as SSF, representing that researchers only need to Scale and Shift the deep Features extracted by a pre-trained model to catch up with the performance of full fine-tuning. In this way, SSF also surprisingly outperforms other parameter-efficient fine-tuning approaches even with a smaller number of tunable parameters. Furthermore, different from some existing parameter-efficient fine-tuning methods (e.g., Adapter or VPT) that introduce the extra parameters and computational cost in the training and inference stages, SSF only adds learnable parameters during the training stage, and these additional parameters can be merged into the original pre-trained model weights via re-parameterization in the inference phase. With the proposed SSF, our model obtains 2.46% (90.72% vs. 88.54%) and 11.48% (73.10% vs. 65.57%) performance improvement on FGVC and VTAB-1k in terms of Top-1 accuracy compared to the full fine-tuning but only fine-tuning about 0.3M parameters. We also conduct amounts of experiments in various model families (CNNs, Transformers, and MLPs) and datasets. Results on 26 image classification datasets in total and 3 robustness & out-of-distribution datasets show the effectiveness of SSF. Code is available at https://github.com/dongzelian/SSF.

For agents

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

get_harvested_code_for_paper("2210.08823")
get_code_for_paper("2210.08823")
have("2210.08823")

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

curl https://syntology.ai/api/ran/2210.08823.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.08823.svg)](https://syntology.ai/paper/2210.08823)

Connect an agent — have() is free.