SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.10728 · ECCV · 2022

Training Vision Transformers with Only 2040 Images

Hao Yu, Wu, Jianxin Wu, Yun-Hao Cao

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 1 has no contract verdict; 0 failures of our instrument; 1 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/2201.10728.json · badge: /api/ran/2201.10728.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
niranjankrishna-acad/Training-Vision-Transformers-with-Only-2040-Images community
Papers with Code archive
1 ran · 0 no recorded run
CupidJay/Training-Vision-Transformers-with-only-2040-images marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
InstanceDiscriminationLoss Ran
ran on a synthesized input
niranjankrishna-acad/Training-Vision-Transformers-with-Only-2040-Images/model.py
code served (permissive licence) · get_code("a0502b13e97543cd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 0, dtype family float; 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 torch.nn as nn

class InstanceDiscriminationLoss(nn.Module):

    def __init__(self):
        super(InstanceDiscriminationLoss, self).__init__()

    def forward(self, predictions):
        return -torch.sum(torch.log(predictions))


INIT_ARGS = {}

ARGS = {
    'predictions': torch.tensor([[0.8, 0.9, 0.7, 0.6], [0.5, 0.4, 0.3, 0.2]], dtype=torch.float32)
}

if __name__ == '__main__':
    loss_fn = InstanceDiscriminationLoss(**INIT_ARGS)
    output = loss_fn(**ARGS)
    print(f"Loss output: {output}")
    print(f"Output shape: {output.shape}")
    print(f"Output type: {type(output)}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SupInstanceDiscrimination Not yet run
unverified (harvested, no recorded run)
CupidJay/Training-Vision-Transformers-with-only-2040-images/utils/supinsdis.py
pointer only (licence: NONE) · get_code("5deea5e57e358c51")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CupidJay/Training-Vision-Transformers-with-only-2040-images 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more data-hungry than common CNNs. They are often pretrained on JFT-300M or at least ImageNet and few works study training ViTs with limited data. In this paper, we investigate how to train ViTs with limited data (e.g., 2040 images). We give theoretical analyses that our method (based on parametric instance discrimination) is superior to other methods in that it can capture both feature alignment and instance similarities. We achieve state-of-the-art results when training from scratch on 7 small datasets under various ViT backbones. We also investigate the transferring ability of small datasets and find that representations learned from small datasets can even improve large-scale ImageNet training.

For agents

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

get_harvested_code_for_paper("2201.10728")
get_code_for_paper("2201.10728")
have("2201.10728")

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

curl https://syntology.ai/api/ran/2201.10728.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.10728.svg)](https://syntology.ai/paper/2201.10728)

Connect an agent — have() is free.