SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.07598 · 2023

AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 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/2303.07598.json · badge: /api/ran/2303.07598.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
maple-research-lab/AdPE canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
build_dataset Ran
ran; our contract draft was wrong, not the code
maple-research-lab/AdPE/data_processing/build_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/mae, is pointer only (licence: NOASSERTION) · get_code("27f8c4c706fd43ec")
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 facebookresearch/mae, and GitHub could not classify the licence of that repository (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.

build_transform Ran
ran; our contract draft was wrong, not the code
maple-research-lab/AdPE/data_processing/build_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/mae, is pointer only (licence: NOASSERTION) · get_code("800cebf161a8aa26")
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 facebookresearch/mae, and GitHub could not classify the licence of that repository (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.

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
build_transform 15 other papers
4 dated earlier, 10 later, 1 same year, order not determinable
2205.03892 (2022-05)
ConvMAE: Masked Convolution Meets Masked Autoencoders
2206.07699 (2022-06)
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
and 12 more not named here
build_dataset 14 other papers
2 dated earlier, 11 later, 1 same year, order not determinable
2205.03892 (2022-05)
ConvMAE: Masked Convolution Meets Masked Autoencoders
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
aaai_25300 (2023 (year only))
Exploring Stochastic Autoregressive Image Modeling for Visual Representation
and 11 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Unsupervised learning of vision transformers seeks to pretrain an encoder via pretext tasks without labels. Among them is the Masked Image Modeling (MIM) aligned with pretraining of language transformers by predicting masked patches as a pretext task. A criterion in unsupervised pretraining is the pretext task needs to be sufficiently hard to prevent the transformer encoder from learning trivial low-level features not generalizable well to downstream tasks. For this purpose, we propose an Adversarial Positional Embedding (AdPE) approach -- It distorts the local visual structures by perturbing the position encodings so that the learned transformer cannot simply use the locally correlated patches to predict the missing ones. We hypothesize that it forces the transformer encoder to learn more discriminative features in a global context with stronger generalizability to downstream tasks. We will consider both absolute and relative positional encodings, where adversarial positions can be imposed both in the embedding mode and the coordinate mode. We will also present a new MAE+ baseline that brings the performance of the MIM pretraining to a new level with the AdPE. The experiments demonstrate that our approach can improve the fine-tuning accuracy of MAE by $0.8\%$ and $0.4\%$ over 1600 epochs of pretraining ViT-B and ViT-L on Imagenet1K. For the transfer learning task, it outperforms the MAE with the ViT-B backbone by $2.6\%$ in mIoU on ADE20K, and by $3.2\%$ in AP$^{bbox}$ and $1.6\%$ in AP$^{mask}$ on COCO, respectively. These results are obtained with the AdPE being a pure MIM approach that does not use any extra models or external datasets for pretraining. The code is available at https://github.com/maple-research-lab/AdPE.

For agents

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

get_harvested_code_for_paper("2303.07598")
get_code_for_paper("2303.07598")
have("2303.07598")

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

curl https://syntology.ai/api/ran/2303.07598.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.07598.svg)](https://syntology.ai/paper/2303.07598)

Connect an agent — have() is free.