SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.09702 · NeurIPS · 2024

On the Surprising Effectiveness of Attention Transfer for Vision Transformers

Deepak Pathak, Beidi Chen, Yuandong Tian, Alexander Li, Xinlei Fair

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 2 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2411.09702.json · badge: /api/ran/2411.09702.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
alexlioralexli/attention-transfer reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input
alexlioralexli/attention-transfer/models_dual_vit.py
pointer only (licence: NOASSERTION) · get_code("66fae84cdc8d8912")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, alexlioralexli/attention-transfer (NOASSERTION). 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.

Block Ran
ran on a synthesized input
alexlioralexli/attention-transfer/models_dual_vit.py
pointer only (licence: NOASSERTION) · get_code("3554200165b73275")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, alexlioralexli/attention-transfer (NOASSERTION). 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.

DualVisionTransformer Not yet run
unverified (harvested, no recorded run)
alexlioralexli/attention-transfer/models_dual_vit.py
pointer only (licence: NOASSERTION) · get_code("cbd765d78399d806")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, alexlioralexli/attention-transfer (NOASSERTION). 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.

VisionTransformer Not yet run
unverified (harvested, no recorded run)
alexlioralexli/attention-transfer/models_dual_vit.py
pointer only (licence: NOASSERTION) · get_code("02bbece47468309a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, alexlioralexli/attention-transfer (NOASSERTION). 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 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, 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 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.

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

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations learned during pre-training are not essential. Surprisingly, using only the attention patterns from pre-training (i.e., guiding how information flows between tokens) is sufficient for models to learn high quality features from scratch and achieve comparable downstream performance. We show this by introducing a simple method called attention transfer, where only the attention patterns from a pre-trained teacher ViT are transferred to a student, either by copying or distilling the attention maps. Since attention transfer lets the student learn its own features, ensembling it with a fine-tuned teacher also further improves accuracy on ImageNet. We systematically study various aspects of our findings on the sufficiency of attention maps, including distribution shift settings where they underperform fine-tuning. We hope our exploration provides a better understanding of what pre-training accomplishes and leads to a useful alternative to the standard practice of fine-tuning. Code to reproduce our results is at https://github.com/alexlioralexli/attention-transfer.

For agents

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

get_harvested_code_for_paper("2411.09702")
get_code_for_paper("2411.09702")
have("2411.09702")

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

curl https://syntology.ai/api/ran/2411.09702.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.09702.svg)](https://syntology.ai/paper/2411.09702)

Connect an agent — have() is free.