SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.01800 · 2020

Temporally Distributed Networks for Fast Video Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

5 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 2 have no contract verdict; 3 failures 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/2004.01800.json · badge: /api/ran/2004.01800.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
feinanshan/TDNet community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
alpha_blend Ran
ran on a synthesized input
feinanshan/TDNet/Training/ptsemseg/utils.py
code served (permissive licence) · get_code("3a8e7e1d2e1dc425")
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 ndarray, ndim 3, dtype family float, shape (4, 5, 3) 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 numpy as np

# Create small test images with 3 channels
# input_image: RGB image as numpy array
input_image = np.random.rand(4, 5, 3).astype(np.float32)

# segmentation_mask: RGB mask as numpy array with same shape
segmentation_mask = np.random.rand(4, 5, 3).astype(np.float32)

# alpha: blending factor
alpha = 0.5

ARGS = {
    "input_image": input_image,
    "segmentation_mask": segmentation_mask,
    "alpha": alpha,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (4, 5, 3) — shape (4, 5, 3) 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
feinanshan/TDNet/Testing/model/pspnet/resnet.py
pointer only (licence: MIT); 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 link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, 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.

recursive_glob Ran
ran; our contract draft was wrong, not the code
feinanshan/TDNet/Training/ptsemseg/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from axi404/pmt, is pointer only (licence: NONE) · get_code("f1e67bfcea91df50")
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 axi404/pmt, 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.

recursive_glob Ran
ran; our contract draft was wrong, not the code
feinanshan/TDNet/Testing/dataloader.py
code served (permissive licence) · get_code("513d282e7c3d723b")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create some subdirectories and files
os.makedirs(os.path.join(temp_dir, 'subdir1'), exist_ok=True)
os.makedirs(os.path.join(temp_dir, 'subdir2'), exist_ok=True)

# Create some test files with various extensions
with open(os.path.join(temp_dir, 'file1.txt'), 'w') as f:
    f.write('test')
with open(os.path.join(temp_dir, 'file2.py'), 'w') as f:
    f.write('test')
with open(os.path.join(temp_dir, 'subdir1', 'file3.txt'), 'w') as f:
    f.write('test')
with open(os.path.join(temp_dir, 'subdir1', 'file4.md'), 'w') as f:
    f.write('test')
with open(os.path.join(temp_dir, 'subdir2', 'file5.txt'), 'w') as f:
    f.write('test')

ARGS = {
    'rootdir': temp_dir,
    'suffix': '.txt'
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
split_fanet_dict Ran
ran on a synthesized input
feinanshan/TDNet/Training/ptsemseg/utils.py
code served (permissive licence) · get_code("acc7d485dfe2d3b1")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from collections import OrderedDict

torch.manual_seed(0)

# Create a sample state_dict with entries for each module type
state_dict = OrderedDict()

# Add resnet backbone entries
state_dict['resnet.layer1.weight'] = torch.randn(4, 3)
state_dict['resnet.layer1.bias'] = torch.randn(4)
state_dict['resnet.layer2.weight'] = torch.randn(8, 4)

# Add ffm_32 entries
state_dict['ffm_32.conv.weight'] = torch.randn(4, 3)
state_dict['ffm_32.conv.bias'] = torch.randn(4)

# Add ffm_16 entries
state_dict['ffm_16.conv.weight'] = torch.randn(4, 3)
state_dict['ffm_16.conv.bias'] = torch.randn(4)

# Add ffm_8 entries
state_dict['ffm_8.conv.weight'] = torch.randn(4, 3)
state_dict['ffm_8.conv.bias'] = torch.randn(4)

# Add ffm_4 entries
state_dict['ffm_4.conv.weight'] = torch.randn(4, 3)
state_dict['ffm_4.conv.bias'] = torch.randn(4)

# Add clslayer_8 (output) entries
state_dict['clslayer_8.weight'] = torch.randn(2, 4)
state_dict['clslayer_8.bias'] = torch.randn(2)

# Add clslayer_32 (output_aux) entries
state_dict['clslayer_32.weight'] = torch.randn(2, 4)
state_dict['clslayer_32.bias'] = torch.randn(2)

ARGS = {
    'state_dict': state_dict,
    'path_num': None
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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

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 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 later) and 1 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
215 dated earlier, 5 the same month, 465 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
recursive_glob 10 other papers
3 dated earlier, 7 later
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1912.13192 (2019-12)
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
2003.09005 (2020-03)
Semi-Supervised Semantic Segmentation with Cross-Consistency Training
and 7 more not named here
alpha_blend 2 other papers
2 later
2006.00176 (2020-06)
When2com: Multi-Agent Perception via Communication Graph Grouping
2106.14917 (2021-06)
Striking the Right Balance: Recall Loss for Semantic Segmentation

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

We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features extracted from several shallower sub-networks. Leveraging the inherent temporal continuity in videos, we distribute these sub-networks over sequential frames. Therefore, at each time step, we only need to perform a lightweight computation to extract a sub-features group from a single sub-network. The full features used for segmentation are then recomposed by application of a novel attention propagation module that compensates for geometry deformation between frames. A grouped knowledge distillation loss is also introduced to further improve the representation power at both full and sub-feature levels. Experiments on Cityscapes, CamVid, and NYUD-v2 demonstrate that our method achieves state-of-the-art accuracy with significantly faster speed and lower latency.

For agents

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

get_harvested_code_for_paper("2004.01800")
get_code_for_paper("2004.01800")
have("2004.01800")

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

curl https://syntology.ai/api/ran/2004.01800.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.01800.svg)](https://syntology.ai/paper/2004.01800)

Connect an agent — have() is free.