SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10120 · 2020

Semantic Flow for Fast and Accurate Scene Parsing

arXiv · PDF · Open in the Atlas

Code that ran

3 of 8 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; 2 failures of our instrument; 5 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/2002.10120.json · badge: /api/ran/2002.10120.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
donnyyou/torchcv canonical (classifier label)
classifier basis: census
2 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
Shualite/SFNet.pytorch reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
FunctionStatusWhere it lives
assert_tensor_type Ran
ran on a synthesized input
donnyyou/torchcv/lib/parallel/data_container.py
code served (permissive licence) · get_code("4a6bd97bd6bba0ad")
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 functools
import torch

def assert_tensor_type(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        if not isinstance(args[0].data, torch.Tensor):
            raise AttributeError('{} has no attribute {} for type {}'.format(args[0].__class__.__name__, func.__name__, args[0].datatype))
        return func(*args, **kwargs)
    return wrapper

torch.manual_seed(0)

class MockObject:
    def __init__(self):
        self.data = torch.randn(2, 4)
        self.datatype = "MockType"

def sample_function(obj):
    return obj.data

mock_obj = MockObject()
decorated_function = assert_tensor_type(sample_function)

ARGS = {
    "func": decorated_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
conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from lixiaotong97/DSU
pointer only; the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

get_input_device Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
donnyyou/torchcv/lib/parallel/_functions.py
code served (permissive licence) · get_code("72b89f53f5854825")
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

torch.manual_seed(0)

# Test case 1: CPU tensor (should return -1)
cpu_tensor = torch.randn(2, 4)

# Test case 2: List containing a CPU tensor
list_with_tensor = [cpu_tensor]

# Test case 3: Nested list with CPU tensor
nested_list = [[cpu_tensor]]

# Test case 4: List with multiple CPU tensors
multiple_tensors = [torch.randn(2, 4), torch.randn(3, 5)]

# Test case 5: Empty list (should return -1)
empty_list = []

ARGS = {
    "input": cpu_tensor
}
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
scatter Not yet run
unverified (harvested, no recorded run)
donnyyou/torchcv/lib/parallel/_functions.py
code served (permissive licence) · get_code("aa73f0787179b863")
How it ran

no invocation recorded.

scatter Not yet run
unverified (harvested, no recorded run)
donnyyou/torchcv/lib/parallel/scatter_gather.py
code served (permissive licence) · get_code("12610892f9cebded")
How it ran

no invocation recorded.

scatter_kwargs Not yet run
unverified (harvested, no recorded run)
donnyyou/torchcv/lib/parallel/scatter_gather.py
code served (permissive licence) · get_code("ea53ec023a304e67")
How it ran

no invocation recorded.

sf_resnet18 Not yet run
unverified (harvested, no recorded run)
Shualite/SFNet.pytorch/sfnet/sfnet.py
code served (permissive licence) · get_code("1b772e24adfd25a7")
How it ran

no invocation recorded.

sf_resnet34 Not yet run
unverified (harvested, no recorded run)
Shualite/SFNet.pytorch/sfnet/sfnet.py
code served (permissive licence) · get_code("b749652595868268")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 later) and 5 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
conv3x3 686 other papers
187 dated earlier, 9 the same month, 489 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
get_input_device 1 other paper
1 later
2105.12085 (2021-05)
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
scatter 1 other paper
1 later
2105.12085 (2021-05)
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation 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 2026-11-22.

Repositories linked to this paper

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

Abstract

In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely used -- atrous convolutions and feature pyramid fusion, are either computation intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level features to high resolution features effectively and efficiently. Furthermore, integrating our module to a common feature pyramid structure exhibits superior performance over other real-time methods even on light-weight backbone networks, such as ResNet-18. Extensive experiments are conducted on several challenging datasets, including Cityscapes, PASCAL Context, ADE20K and CamVid. Especially, our network is the first to achieve 80.4\% mIoU on Cityscapes with a frame rate of 26 FPS. The code is available at \url{https://github.com/lxtGH/SFSegNets}.

For agents

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

get_harvested_code_for_paper("2002.10120")
get_code_for_paper("2002.10120")
have("2002.10120")

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

curl https://syntology.ai/api/ran/2002.10120.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.10120.svg)](https://syntology.ai/paper/2002.10120)

Connect an agent — have() is free.