SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1707.03718 · 2017

LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 3 failures of our instrument; 1 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/1707.03718.json · badge: /api/ran/1707.03718.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
qubvel/segmentation_models reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
fourmi1995/IronSegExperiment-LinkNet reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Conv1x1BnReLU Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from qubvel/segmentation_models
pointer only · get_code("6967c6e3ddb59aa2")
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.

Conv3x3BnReLU Ran
ran; our contract draft was wrong, not the code
qubvel/segmentation_models/segmentation_models/models/linknet.py
code served (permissive licence) · get_code("1a48303fff043b85")
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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class MockBackend:
    def __init__(self):
        pass

class MockLayers:
    def __init__(self):
        pass
    
    @staticmethod
    def Conv2D(*args, **kwargs):
        return nn.Conv2d(kwargs.get('filters', 32), kwargs.get('filters', 32), kernel_size=3, padding=1)
    
    @staticmethod
    def BatchNormalization(*args, **kwargs):
        return nn.BatchNorm2d(kwargs.get('filters', 32))
    
    @staticmethod
    def Activation(*args, **kwargs):
        return nn.ReLU()

class MockModels:
    def __init__(self):
        pass

class MockKerasUtils:
    def __init__(self):
        pass

class MockConv2dBn(nn.Module):
    def __init__(self, filters, kernel_size=3, activation='relu', kernel_initializer='he_uniform', 
                 padding='same', use_batchnorm=True, name=None, backend=None, models=None, 
                 layers=None, utils=None):
        super().__init__()
        self.filters = filters
        self.kernel_size = kernel_size
        self.activation = activation
        self.kernel_initializer = kernel_initializer
        self.padding = padding
        self.use_batchnorm = use_batchnorm
        self.name = name
        
        # Create a simple conv layer
        pad = 1 if padding == 'same' else 0
        self.conv = nn.Conv2d(3, filters, kernel_size=kernel_size, padding=pad)
        
        if use_batchnorm:
            self.bn = nn.BatchNorm2d(filters)
        else:
            self.bn = None
        
        if activation == 'relu':
            self.act = nn.ReLU()
        else:
            self.act = None
    
    def forward(self, x):
        x = self.conv(x)
        if self.bn is not None:
            x = self.bn(x)
        if self.act is not None:
            x = self.act(x)
        return x

# Mock the Conv2dBn function
def Conv2dBn(filters, kernel_size=3, activation='relu', kernel_initializer='he_uniform', 
             padding='same', use_batchnorm=True, name=None, **kwargs):
    return MockConv2dBn(filters, kernel_size=kernel_size, activation=activation, 
                        kernel_initializer=kernel_initializer, padding=padding, 
                        use_batchnorm=use_batchnorm, name=name, **kwargs)

# Set up global module references
backend = MockBackend()
layers = MockLayers()
models = MockModels()
keras_utils = MockKerasUtils()

ARGS = {
    'filters': 32,
    'use_batchnorm': True,
    'name': 'conv3x3_bn_relu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
walk_dir Ran
ran; our contract draft was wrong, not the code
fourmi1995/IronSegExperiment-LinkNet/code/segmentation.py
pointer only (licence: NONE) · get_code("d57782f4d096bc7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fourmi1995/IronSegExperiment-LinkNet 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.

DecoderUpsamplingX2Block Not yet run
unverified (harvested, no recorded run)
qubvel/segmentation_models/segmentation_models/models/linknet.py
code served (permissive licence) · get_code("f405eb0f965c94cd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 3 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
Conv1x1BnReLU 1 other paper
1 dated earlier
1612.01105 (2016-12)
Pyramid Scene Parsing Network

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

Pixel-wise semantic segmentation for visual scene understanding not only needs to be accurate, but also efficient in order to find any use in real-time application. Existing algorithms even though are accurate but they do not focus on utilizing the parameters of neural network efficiently. As a result they are huge in terms of parameters and number of operations; hence slow too. In this paper, we propose a novel deep neural network architecture which allows it to learn without any significant increase in number of parameters. Our network uses only 11.5 million parameters and 21.2 GFLOPs for processing an image of resolution 3x640x360. It gives state-of-the-art performance on CamVid and comparable results on Cityscapes dataset. We also compare our networks processing time on NVIDIA GPU and embedded system device with existing state-of-the-art architectures for different image resolutions.

For agents

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

get_harvested_code_for_paper("1707.03718")
get_code_for_paper("1707.03718")
have("1707.03718")

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

curl https://syntology.ai/api/ran/1707.03718.json

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

[![Syntology run record](https://syntology.ai/api/ran/1707.03718.svg)](https://syntology.ai/paper/1707.03718)

Connect an agent — have() is free.