SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.06202 · AAAI · 2020

FedVision: An Online Visual Object Detection Platform Powered by Federated Learning

Yang Liu, Qiang Yang, Tianjian Chen, He Huang, Han Yu, Yuanyuan Chen, Yun Luo, Anbu Huang, Youzhi Liu, Lican Feng

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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 3 have no contract verdict; 1 failure of our instrument; 1 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/2001.06202.json · badge: /api/ran/2001.06202.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
ShenSuanZiZhen/NIID_Person_Detection community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
GET_BLOCKS Ran
ran on a synthesized input
ShenSuanZiZhen/NIID_Person_Detection/model/roi_module.py
code served (permissive licence) · get_code("7ec4ccbecab27688")
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 int, ndim 0, dtype family int, shape () 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

CUDA_NUM_THREADS = 1024

def GET_BLOCKS(N, K=CUDA_NUM_THREADS):
    return (N + K - 1) // K

# Setup code
torch.manual_seed(0)

# N is an integer representing the number of elements to process
N = 2048

# K is an integer representing the number of threads per block (defaults to CUDA_NUM_THREADS)
K = 512

ARGS = {
    "N": N,
    "K": K
}
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 int, ndim 0, dtype family int, shape () — shape () 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
load_json Ran
ran; our contract draft was wrong, not the code
ShenSuanZiZhen/NIID_Person_Detection/fl_client.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from hoeng4/PruneCD, is pointer only (licence: NONE) · get_code("d0bb7013dd302153")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from hoeng4/PruneCD, and GitHub detected no licence in that repository 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. A run is recorded.

nograd Ran
ran on a synthesized input
ShenSuanZiZhen/NIID_Person_Detection/model/faster_rcnn.py
code served (permissive licence) · get_code("2a631501adce8730")
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 function. 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 as t

t.manual_seed(0)

# The function `nograd` is a decorator that wraps a function `f` to execute it
# within torch.no_grad() context. It takes a single parameter `f` which should
# be a callable (function).

# Create a simple test function to pass as the parameter
def sample_function(x, y):
    """A simple function that performs some tensor operations."""
    return x + y

ARGS = {
    "f": sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
pickle_string_to_obj Ran
ran on a synthesized input
ShenSuanZiZhen/NIID_Person_Detection/utils/model_dump.py
code served (permissive licence) · get_code("91a704e6c3d35218")
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 dict. 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 pickle
import codecs
import base64

# Create a simple object to pickle
test_obj = {"key": "value", "number": 42, "list": [1, 2, 3]}

# Create a base64-encoded pickled string (not a file path)
pickled_bytes = pickle.dumps(test_obj)
encoded_string = codecs.encode(pickled_bytes, 'base64').decode()

ARGS = {
    "s": encoded_string
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
obj_to_pickle_string Not yet run
unverified (harvested, no recorded run)
ShenSuanZiZhen/NIID_Person_Detection/utils/model_dump.py
code served (permissive licence) · get_code("99a33392b1325b9c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 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
load_json 3 other papers
1 dated earlier, 2 later
1910.11089 (2019-10)
Real-World Image Datasets for Federated Learning
2504.04635 (2025-04)
Steering off Course: Reliability Challenges in Steering Language Models
2509.16598 (2025-09)
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
nograd 2 other papers
1 dated earlier, 1 later
1910.11089 (2019-10)
Real-World Image Datasets for Federated Learning
2302.09491 (2023-02)
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection
GET_BLOCKS 1 other paper
1 dated earlier
1910.11089 (2019-10)
Real-World Image Datasets for Federated Learning
obj_to_pickle_string 1 other paper
1 dated earlier
1910.11089 (2019-10)
Real-World Image Datasets for Federated Learning
pickle_string_to_obj 1 other paper
1 dated earlier
1910.11089 (2019-10)
Real-World Image Datasets for Federated Learning

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

Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (e.g., fire hazard monitoring). However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored large training datasets following the current approach. Federated learning (FL) is a promising approach to resolve this challenge. Nevertheless, there currently lacks an easy to use tool to enable computer vision application developers who are not experts in federated learning to conveniently leverage this technology and apply it in their systems. In this paper, we report FedVision -a machine learning engineering platform to support the development of federated learning powered computer vision applications. The platform has been deployed through a collaboration between WeBank and Extreme Vision to help customers develop computer vision-based safety monitoring solutions in smart city applications. Over four months of usage, it has achieved significant efficiency improvement and cost reduction while removing the need to transmit sensitive data for three major corporate customers. To the best of our knowledge, this is the first real application of FL in computer vision-based tasks.

For agents

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

get_harvested_code_for_paper("2001.06202")
get_code_for_paper("2001.06202")
have("2001.06202")

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

curl https://syntology.ai/api/ran/2001.06202.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.06202.svg)](https://syntology.ai/paper/2001.06202)

Connect an agent — have() is free.