SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.13097 · NeurIPS · 2021

Rotation Equivariant Deforestation Segmentation and Driver Classification

Joshua Mitton, Roderick Murray-Smith

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 0 failures of our instrument; 2 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/2110.13097.json · badge: /api/ran/2110.13097.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
joshuamitton/rotation-equivariant-deforestation-segmentation canonical (classifier label)
classifier basis: classifier_2025
3 ran · 2 no recorded run
FunctionStatusWhere it lives
DoubleConv Ran
ran on a synthesized input
joshuamitton/rotation-equivariant-deforestation-segmentation/roteqseg/eq_models.py
code served (permissive licence) · get_code("0e6c4dcb80d07666")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned GeometricTensor. 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
from e2cnn import gspaces
from e2cnn import nn as e2nn

# Define the group and representation space
gspace = gspaces.Rot2dOnR2(N=4)  # 4 rotations (90 degree symmetry)

# Create field types for input and output channels
# FieldType wraps the group space and specifies the representation
in_type = e2nn.FieldType(gspace, [gspace.trivial_repr] * 3)  # 3 input channels, trivial representation
mid_type = e2nn.FieldType(gspace, [gspace.regular_repr] * 2)  # 2 mid channels with regular representation
out_type = e2nn.FieldType(gspace, [gspace.regular_repr] * 2)  # 2 output channels with regular representation

INIT_ARGS = {
    'in_channels': in_type,
    'out_channels': out_type,
    'mid_channels': mid_type
}

# Create input tensor as GeometricTensor
# Batch size 2, spatial dimensions 8x6
batch_size = 2
height = 8
width = 6
input_tensor = torch.randn(batch_size, in_type.size, height, width)
input_geometric = e2nn.GeometricTensor(input_tensor, in_type)

ARGS = {
    'x': input_geometric
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
e2cnn, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GeometricTensor — a GeometricTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GeometricTensor 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Down Ran
ran on a synthesized input
joshuamitton/rotation-equivariant-deforestation-segmentation/roteqseg/eq_models.py
code served (permissive licence) · get_code("7f58121dae4532e3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned GeometricTensor. 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
from e2cnn import gspaces
from e2cnn import nn as e2nn

# Define the group and representation space
r2_act = gspaces.Rot2dOnR2(N=4)  # 4 rotations (90 degree symmetry)

# Create field types for input and output channels
in_type = e2nn.FieldType(r2_act, [r2_act.trivial_repr] * 3)  # 3 input channels
mid_type = e2nn.FieldType(r2_act, [r2_act.regular_repr] * 2)  # 2*4=8 mid channels
out_type = e2nn.FieldType(r2_act, [r2_act.regular_repr] * 3)  # 3*4=12 out channels

INIT_ARGS = {
    'in_channels': in_type,
    'out_channels': out_type
}

# Create input tensor wrapped in GeometricTensor
batch_size = 2
height = 16
width = 16
input_tensor = torch.randn(batch_size, in_type.size, height, width)
input_geom = e2nn.GeometricTensor(input_tensor, in_type)

ARGS = {
    'x': input_geom
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
e2cnn, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GeometricTensor — a GeometricTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GeometricTensor 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
OutConv Ran
ran on a synthesized input
joshuamitton/rotation-equivariant-deforestation-segmentation/roteqseg/eq_models.py
code served (permissive licence) · get_code("b2af37a624291601")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned GeometricTensor. 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
from e2cnn import gspaces
from e2cnn import nn as e2nn

# Create a rotation group (cyclic group of order 4 for 90-degree rotations)
r2_act = gspaces.Rot2dOnR2(N=4)

# Define input and output feature types
# Using regular representation for simplicity
in_type = e2nn.FieldType(r2_act, [r2_act.regular_repr] * 2)
out_type = e2nn.FieldType(r2_act, [r2_act.regular_repr] * 3)

INIT_ARGS = {
    'in_channels': in_type,
    'out_channels': out_type,
}

# Create a geometric tensor with shape (batch, channels, height, width)
# batch=2, channels match in_type.size, height=4, width=3
batch_size = 2
height = 4
width = 3
num_channels = in_type.size

input_tensor = e2nn.GeometricTensor(
    torch.randn(batch_size, num_channels, height, width),
    in_type
)

ARGS = {
    'x': input_tensor,
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
e2cnn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GeometricTensor — a GeometricTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GeometricTensor 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
UNet_eq Not yet run
unverified (harvested, no recorded run)
joshuamitton/rotation-equivariant-deforestation-segmentation/roteqseg/eq_models.py
code served (permissive licence) · get_code("426191698a019fbc")
How it ran

no invocation recorded.

Up Not yet run
unverified (harvested, no recorded run)
joshuamitton/rotation-equivariant-deforestation-segmentation/roteqseg/eq_models.py
code served (permissive licence) · get_code("1e2a08e96eeebf1d")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Deforestation has become a significant contributing factor to climate change and, due to this, both classifying the drivers and predicting segmentation maps of deforestation has attracted significant interest. In this work, we develop a rotation equivariant convolutional neural network model to predict the drivers and generate segmentation maps of deforestation events from Landsat 8 satellite images. This outperforms previous methods in classifying the drivers and predicting the segmentation map of deforestation, offering a 9% improvement in classification accuracy and a 7% improvement in segmentation map accuracy. In addition, this method predicts stable segmentation maps under rotation of the input image, which ensures that predicted regions of deforestation are not dependent upon the rotational orientation of the satellite.

For agents

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

get_harvested_code_for_paper("2110.13097")
get_code_for_paper("2110.13097")
have("2110.13097")

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

curl https://syntology.ai/api/ran/2110.13097.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.13097.svg)](https://syntology.ai/paper/2110.13097)

Connect an agent — have() is free.