SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.05850 · 2024

Scaling Graph Convolutions for Mobile Vision

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure of our instrument; 0 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/2406.05850.json · badge: /api/ran/2406.05850.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
sldgroup/mobilevigv2 canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
reparameterize_model Ran
ran; our contract draft was wrong, not the code
sldgroup/mobilevigv2/detection/mobilevigv2_backbone.py
code served (permissive licence) · get_code("4fa955209433f46d")
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 MobileOneModel. 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
import copy

torch.manual_seed(0)

class ReparameterizableModule(nn.Module):
    """A simple module with a reparameterize method"""
    def __init__(self):
        super().__init__()
        self.weight = nn.Parameter(torch.randn(4, 3))
        self.has_reparameterized = False
    
    def reparameterize(self):
        """Reparameterize this module for inference"""
        self.has_reparameterized = True
        self.weight.data = self.weight.data * 2
    
    def forward(self, x):
        return x @ self.weight.t()

class MobileOneModel(nn.Module):
    """Minimal MobileOne-like model with reparameterizable branches"""
    def __init__(self):
        super().__init__()
        self.branch1 = ReparameterizableModule()
        self.branch2 = ReparameterizableModule()
        self.linear = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear(self.branch1(x))

# Create a minimal model that the function can work with
model = MobileOneModel()

ARGS = {
    'model': model
}
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 MobileOneModel — a MobileOneModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileOneModel 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 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
reparameterize_model 3 other papers
3 dated earlier
2203.03339 (2022-03)
L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments
2206.04040 (2022-06)
MobileOne: An Improved One millisecond Mobile Backbone
2309.03452 (2023-09)
Multimodal Guidance Network for Missing-Modality Inference in Content Moderation

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

To compete with existing mobile architectures, MobileViG introduces Sparse Vision Graph Attention (SVGA), a fast token-mixing operator based on the principles of GNNs. However, MobileViG scales poorly with model size, falling at most 1% behind models with similar latency. This paper introduces Mobile Graph Convolution (MGC), a new vision graph neural network (ViG) module that solves this scaling problem. Our proposed mobile vision architecture, MobileViGv2, uses MGC to demonstrate the effectiveness of our approach. MGC improves on SVGA by increasing graph sparsity and introducing conditional positional encodings to the graph operation. Our smallest model, MobileViGv2-Ti, achieves a 77.7% top-1 accuracy on ImageNet-1K, 2% higher than MobileViG-Ti, with 0.9 ms inference latency on the iPhone 13 Mini NPU. Our largest model, MobileViGv2-B, achieves an 83.4% top-1 accuracy, 0.8% higher than MobileViG-B, with 2.7 ms inference latency. Besides image classification, we show that MobileViGv2 generalizes well to other tasks. For object detection and instance segmentation on MS COCO 2017, MobileViGv2-M outperforms MobileViG-M by 1.2 $AP^{box}$ and 0.7 $AP^{mask}$, and MobileViGv2-B outperforms MobileViG-B by 1.0 $AP^{box}$ and 0.7 $AP^{mask}$. For semantic segmentation on ADE20K, MobileViGv2-M achieves 42.9% $mIoU$ and MobileViGv2-B achieves 44.3% $mIoU$. Our code can be found at \url{https://github.com/SLDGroup/MobileViGv2}.

For agents

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

get_harvested_code_for_paper("2406.05850")
get_code_for_paper("2406.05850")
have("2406.05850")

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

curl https://syntology.ai/api/ran/2406.05850.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.05850.svg)](https://syntology.ai/paper/2406.05850)

Connect an agent — have() is free.