SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.10366 · 2024

Accessing Vision Foundation Models via ImageNet-1K

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 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; 2 failures of our instrument; 6 no recorded run), measured 2026-11-21; 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/2407.10366.json · badge: /api/ran/2407.10366.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
bespontaneous/proteus-pytorch canonical (classifier label)
classifier basis: census
4 ran · 6 no recorded run
FunctionStatusWhere it lives
compute_gather_ids Ran
ran, honoured the contract we drafted
bespontaneous/proteus-pytorch/pretrain/models_synclr.py
code served (permissive licence) · get_code("c2c9f9c2836ca88a")
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 int, shape (2, 6) 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 expects masks as a tensor with shape (batch_size, ...).
# It calls:
# - masks.logical_not() -> returns a boolean tensor
# - .nonzero(as_tuple=False) -> returns indices of True values
# - indexing with [:, -1] -> gets last dimension indices
# - .reshape(masks.shape[0], -1) -> reshapes to (batch_size, -1)
#
# For this to work, masks should be a boolean tensor with at least 2 dimensions.
# Let's create a batch of 2 boolean masks with shape (2, 3, 4)

masks = torch.tensor([
    [[True, False, True, False],
     [False, True, False, True],
     [True, True, False, False]],
    [[False, False, True, True],
     [True, False, False, True],
     [False, True, True, False]]
], dtype=torch.bool)

ARGS = {
    "masks": masks
}
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 int, shape (2, 6) — shape (2, 6) 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
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bespontaneous/proteus-pytorch/pretrain/models_dinov2.py
code served (permissive licence) · get_code("c157f5b112b3a392")
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) 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

torch.manual_seed(0)

# Create a small tensor for drop_path
# The function uses x.shape[0] for batch dimension and x.ndim for number of dimensions
# It also calls x.new_empty() and performs element-wise operations
x = torch.randn(2, 4, 3, 5)  # batch=2, then 3 other dimensions with distinct sizes

ARGS = {
    "x": x,
    "drop_prob": 0.5,
    "training": True
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
make_2tuple Ran
ran, honoured the contract we drafted
bespontaneous/proteus-pytorch/pretrain/models_dinov2.py
code served (permissive licence) · get_code("3c04490a215299f2")
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, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

# Test case 1: tuple input with length 2
test_tuple = (5, 7)

# Test case 2: integer input
test_int = 3

# We'll create ARGS with the integer case
ARGS = {
    "x": test_int
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
named_apply Ran
ran; our contract draft was wrong, not the code
bespontaneous/proteus-pytorch/pretrain/models_clip.py
code served (permissive licence) · get_code("7ebead3a3a2008d4")
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 SimpleModel. 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)

# Define a simple callback function that will be applied to modules
def callback_fn(module, name):
    """Simple callback that tracks which modules it's called on"""
    pass

# Build a small nested nn.Module
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
        self.nested = nn.Sequential(
            nn.Linear(2, 4),
            nn.ReLU()
        )
    
    def forward(self, x):
        return x

# Instantiate the model
module = SimpleModel()

# Define all arguments for named_apply
ARGS = {
    'fn': callback_fn,
    'module': module,
    'name': '',
    'depth_first': True,
    'include_root': False
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
drop_add_residual_stochastic_depth Not yet run
unverified (harvested, no recorded run)
bespontaneous/proteus-pytorch/pretrain/models_dinov2.py
code served (permissive licence) · get_code("fe3002776da59ed1")
How it ran

no invocation recorded.

has_ddp_wrapper Not yet run
unverified (harvested, no recorded run)
bespontaneous/proteus-pytorch/eval/ImageNet_probing/dinov2/eval/linear_proteus.py
code served (permissive licence) · get_code("1cd2728a84872357")
How it ran

no invocation recorded.

remove_ddp_wrapper Not yet run
unverified (harvested, no recorded run)
bespontaneous/proteus-pytorch/eval/ImageNet_probing/dinov2/eval/linear_proteus.py
code served (permissive licence) · get_code("f565e9c6316d8c64")
How it ran

no invocation recorded.

vit_base Not yet run
unverified (harvested, no recorded run)
bespontaneous/proteus-pytorch/pretrain/models_clip.py
code served (permissive licence) · get_code("3ded69e796e2adc1")
How it ran

no invocation recorded.

vit_base Not yet run
unverified (harvested, no recorded run)
bespontaneous/proteus-pytorch/pretrain/models_synclr.py
code served (permissive licence) · get_code("7eb323949f069bd6")
How it ran

no invocation recorded.

vit_small Not yet run
unverified (harvested, no recorded run)
bespontaneous/proteus-pytorch/pretrain/models_clip.py
code served (permissive licence) · get_code("111664a7e8f9164c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 6 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.

FunctionAlso present inEarliest-datedOthers named
named_apply 26 other papers
10 dated earlier, 1 the same month, 13 later, 2 undated
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2204.07683 (2022-04)
Safe Self-Refinement for Transformer-based Domain Adaptation
2304.07193 (2023-04)
DINOv2: Learning Robust Visual Features without Supervision
and 23 more not named here
drop_add_residual_stochastic_depth 21 other papers
8 dated earlier, 2 the same month, 9 later, 2 undated
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2304.07193 (2023-04)
DINOv2: Learning Robust Visual Features without Supervision
2312.02366 (2023-12)
Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks
and 18 more not named here
make_2tuple 20 other papers
6 dated earlier, 3 the same month, 10 later, 1 undated · 1 only as an assembly brick
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2304.07193 (2023-04)
DINOv2: Learning Robust Visual Features without Supervision
2312.02366 (2023-12)
Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks
and 17 more not named here
drop_path 18 other papers
6 dated earlier, 3 the same month, 8 later, 1 undated · 2 only as an assembly brick
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2304.07193 (2023-04)
DINOv2: Learning Robust Visual Features without Supervision
2312.02366 (2023-12)
Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks
and 15 more not named here
has_ddp_wrapper 5 other papers
2 dated earlier, 3 later
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2309.16588 (2023-09)
Vision Transformers Need Registers
2505.12191 (2025-05)
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
and 2 more not named here
remove_ddp_wrapper 4 other papers
2 dated earlier, 2 later
2103.00020 (2021-03)
Learning Transferable Visual Models From Natural Language Supervision
2309.16588 (2023-09)
Vision Transformers Need Registers
2505.12191 (2025-05)
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
and 1 more not named here

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Vision foundation models are renowned for the generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is often inaccessible, e.g., CLIP, DINOv2, posing great challenges to developing derivatives that could facilitate the research. In this work, we offer a very simple and general solution, named \textit{Proteus}, to distill foundation models into smaller equivalents on ImageNet-1K without access to the original training data. Specifically, we remove the designs from conventional knowledge distillation settings that result in dataset bias and present three levels of training objectives, i.e., token, patch, and feature, to maximize the efficacy of knowledge transfer. In this manner, Proteus is trained at ImageNet-level costs with surprising ability, facilitating the accessibility of training foundation models for the broader research community. When leveraging DINOv2-g/14 as the teacher, Proteus-L/14 matches the performance of the Oracle method DINOv2-L/14 (142M training data) across 19 benchmarks and outperforms other vision foundation models including CLIP-L/14 (400M), OpenCLIP-L/14 (400M/2B) and SynCLR-L/14 (600M) with a significantly smaller training set of 1.2M images.

For agents

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

get_harvested_code_for_paper("2407.10366")
get_code_for_paper("2407.10366")
have("2407.10366")

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

curl https://syntology.ai/api/ran/2407.10366.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.10366.svg)](https://syntology.ai/paper/2407.10366)

Connect an agent — have() is free.