SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.11065 · 2019

Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 4 failures of our instrument; 4 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/1909.11065.json · badge: /api/ran/1909.11065.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
openseg-group/openseg.pytorch canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
HRNet/HRNet-Semantic-Segmentation canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
rosinality/ocr-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
Burf/HRNetV2-OCR-Tensorflow2 community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
conv1d Ran
ran; our contract draft was wrong, not the code
rosinality/ocr-pytorch/model.py
code served (permissive licence) · get_code("ab8dda773f3d5789")
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) and returned Sequential. 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

torch.manual_seed(0)

ARGS = {
    "in_channel": 3,
    "out_channel": 16,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
conv2d Ran
ran; our contract draft was wrong, not the code
rosinality/ocr-pytorch/model.py
code served (permissive licence) · get_code("9333dd68e11e060d")
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) and returned Sequential. 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

torch.manual_seed(0)

ARGS = {
    "in_channel": 3,
    "out_channel": 16,
    "kernel_size": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
HRNet/HRNet-Semantic-Segmentation/lib/models/seg_hrnet.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, HRNet/HRNet-Semantic-Segmentation 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.

generateInstanceStats Ran
ran; our contract draft was wrong, not the code
openseg-group/openseg.pytorch/lib/metrics/cityscapes/evaluation/evalPixelLevelSemanticLabeling.py
code served (permissive licence) · get_code("7d4554a0bd6eb4d2")
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) 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 torch
import numpy as np

# Define a minimal Label class that matches what the function expects
class Label:
    def __init__(self, name, label_id, has_instances, ignore_in_eval):
        self.name = name
        self.id = label_id
        self.hasInstances = has_instances
        self.ignoreInEval = ignore_in_eval

# Create sample labels
label_person = Label("person", 0, True, False)
label_car = Label("car", 1, True, False)
label_road = Label("road", 2, False, False)
label_sky = Label("sky", 3, True, True)
label_void = Label("void", -1, False, False)

labels = [label_person, label_car, label_road, label_sky, label_void]

# Create category to labels mapping
category2labels = {
    "human": [label_person],
    "vehicle": [label_car],
    "stuff": [label_road, label_sky],
}

# Create a minimal args object/dict
class Args:
    pass

args = Args()
args.labels = labels
args.category2labels = category2labels

# Make labels and category2labels accessible at module level for the function
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'labels', labels)
setattr(current_module, 'category2labels', category2labels)

ARGS = {
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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
hr_transition_block Ran
ran on a synthesized input
Burf/HRNetV2-OCR-Tensorflow2/hrnet/hrnet.py
code served (permissive licence) · get_code("05831920f7a920c9")
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. 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)
np.random.seed(0)

# Create small input tensors with distinct spatial dimensions
# Using batch=2, height=4, width=3, channels=1
input_tensor_1 = tf.random.normal((2, 4, 3, 1))
input_tensor_2 = tf.random.normal((2, 4, 3, 2))

ARGS = {
    'x': [input_tensor_1, input_tensor_2],
    'n_feature': 8,
    'kwargs': {}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is 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
generateMatrix Not yet run
unverified (harvested, no recorded run)
openseg-group/openseg.pytorch/lib/metrics/cityscapes/evaluation/evalPixelLevelSemanticLabeling.py
code served (permissive licence) · get_code("83f120a07b1755b4")
How it ran

no invocation recorded.

getPrediction Not yet run
unverified (harvested, no recorded run)
openseg-group/openseg.pytorch/lib/metrics/cityscapes/evaluation/evalPixelLevelSemanticLabeling.py
code served (permissive licence) · get_code("a9c50973bbd521dc")
How it ran

no invocation recorded.

hr_basic_block Not yet run
unverified (harvested, no recorded run)
Burf/HRNetV2-OCR-Tensorflow2/hrnet/hrnet.py
code served (permissive licence) · get_code("6b491db5a0440458")
How it ran

no invocation recorded.

hr_bottleneck_block Not yet run
unverified (harvested, no recorded run)
Burf/HRNetV2-OCR-Tensorflow2/hrnet/hrnet.py
code served (permissive licence) · get_code("be1dcef7d7100993")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 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
154 dated earlier, 8 the same month, 524 later · 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
generateInstanceStats 1 other paper
1 later
2006.07864 (2020-06)
Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection
generateMatrix 1 other paper
1 later
2006.07864 (2020-06)
Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection
getPrediction 1 other paper
1 later
2006.07864 (2020-06)
Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection

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 address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to. We present a simple yet effective approach, object-contextual representations, characterizing a pixel by exploiting the representation of the corresponding object class. First, we learn object regions under the supervision of ground-truth segmentation. Second, we compute the object region representation by aggregating the representations of the pixels lying in the object region. Last, % the representation similarity we compute the relation between each pixel and each object region and augment the representation of each pixel with the object-contextual representation which is a weighted aggregation of all the object region representations according to their relations with the pixel. We empirically demonstrate that the proposed approach achieves competitive performance on various challenging semantic segmentation benchmarks: Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff. Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff. Our submission "HRNet + OCR + SegFix" achieves 1-st place on the Cityscapes leaderboard by the time of submission. Code is available at: https://git.io/openseg and https://git.io/HRNet.OCR. We rephrase the object-contextual representation scheme using the Transformer encoder-decoder framework. The details are presented in~Section3.3.

For agents

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

get_harvested_code_for_paper("1909.11065")
get_code_for_paper("1909.11065")
have("1909.11065")

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

curl https://syntology.ai/api/ran/1909.11065.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.11065.svg)](https://syntology.ai/paper/1909.11065)

Connect an agent — have() is free.