SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.16607 · ICCV · 2021

Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data

Alexandre Lacoste, Xavier Giró-I-Nieto, David Vazquez, Pau Rodriguez, Oscar Mañas

arXiv · PDF · Open in the Atlas

Code that ran

5 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 2 have no contract verdict; 3 failures of our instrument; 3 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/2103.16607.json · badge: /api/ran/2103.16607.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
ElementAI/seasonal-contrast canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
floatingstarZ/GeRSP community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
servicenow/seasonal-contrast community (classifier label)
classifier basis: plan_row
0 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_accuracy Ran
ran on a synthesized input
floatingstarZ/GeRSP/mmselfsup/models/algorithms/moco_gersp.py
code served (permissive licence) · get_code("2ea140a31f1421c4")
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 2, 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

torch.manual_seed(0)

# Create a small batch of classification outputs (logits)
# batch_size=2, num_classes=4
output = torch.randn(2, 4)

# Create target labels (class indices)
target = torch.tensor([1, 3])

# Define topk parameter
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
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 list, ndim 2, 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
get_experiment_name Ran
ran; our contract draft was wrong, not the code
ElementAI/seasonal-contrast/main_bigearthnet.py
code served (permissive licence) · get_code("8cea7a513c856e17")
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 str. 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)

class HParams:
    def __init__(self, freeze_backbone, learning_rate, max_epochs, train_frac):
        self.freeze_backbone = freeze_backbone
        self.learning_rate = learning_rate
        self.max_epochs = max_epochs
        self.train_frac = train_frac

hparams = HParams(
    freeze_backbone=False,
    learning_rate=0.001,
    max_epochs=100,
    train_frac=0.8
)

ARGS = {
    'prefix': 'experiment',
    'hparams': hparams
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_experiment_name Ran
ran; our contract draft was wrong, not the code
ElementAI/seasonal-contrast/main_pretrain.py
code served (permissive licence) · get_code("da02260fb5561b46")
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 str. 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 os
from pathlib import Path

class HParams:
    def __init__(self):
        self.data_dir = "/path/to/dataset_name"
        self.base_encoder = "resnet50"
        self.data_mode = "supervised"
        self.max_epochs = 100

hparams = HParams()

ARGS = {
    "hparams": hparams
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_segmentation_model Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ElementAI/seasonal-contrast/models/segmentation.py
code served (permissive licence) · get_code("47e0aa4f82fd7af1")
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 UNet. 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)

# Create a minimal backbone as a Sequential module
# The backbone will have several layers that can be indexed
backbone = nn.Sequential(
    nn.Conv2d(3, 16, kernel_size=3, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(2, 2),
    nn.Conv2d(16, 32, kernel_size=3, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(2, 2),
    nn.Conv2d(32, 64, kernel_size=3, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(2, 2),
    nn.Conv2d(64, 128, kernel_size=3, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(2, 2),
    nn.Conv2d(128, 256, kernel_size=3, padding=1),
    nn.ReLU(),
)

# Feature indices to extract from backbone
# These should be indices where we want to capture intermediate features
feature_indices = [0, 2, 4, 6, 8, 10]

# Feature channels corresponding to each extracted feature
# Must match the number of features extracted (len(feature_indices))
feature_channels = [16, 32, 64, 128, 256, 512]

ARGS = {
    'backbone': backbone,
    'feature_indices': feature_indices,
    'feature_channels': feature_channels,
}
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 UNet — a UNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a UNet 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
normalize Ran
ran on a synthesized input
ElementAI/seasonal-contrast/datasets/bigearthnet_dataset.py
code served (permissive licence) · get_code("15c4c0f9b256fee4")
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 2, dtype family int, shape (4, 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 sample image data as a numpy array
img = np.random.rand(4, 3) * 100  # Small 4x3 image with values in range [0, 100]

# Define normalization parameters
mean = 50.0
std = 10.0

ARGS = {
    "img": img,
    "mean": mean,
    "std": std,
}
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 2, dtype family int, shape (4, 3) — shape (4, 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
batch_shuffle_ddp Not yet run
unverified (harvested, no recorded run)
servicenow/seasonal-contrast/models/moco2_module.py
code served (permissive licence) · get_code("35c74641cae2d081")
How it ran

no invocation recorded.

batch_unshuffle_ddp Not yet run
unverified (harvested, no recorded run)
ElementAI/seasonal-contrast/models/moco2_module.py
code served (permissive licence) · get_code("84c3492f31564f3e")
How it ran

no invocation recorded.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
ElementAI/seasonal-contrast/models/moco2_module.py
code served (permissive licence) · get_code("73cecca9f3575f09")
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, 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 4 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
concat_all_gather 138 other papers
13 dated earlier, 2 the same month, 121 later, 2 same year, order not determinable · 33 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 135 more not named here
batch_shuffle_ddp 2 other papers
2 later
2211.15059 (2022-11)
Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
2312.03533 (2023-12)
Low-shot Object Learning with Mutual Exclusivity Bias
batch_unshuffle_ddp 2 other papers
2 later
2211.15059 (2022-11)
Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
2411.02256 (2024-11)
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
normalize 1 other paper
1 later
2306.09424 (2023-06)
SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

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

Remote sensing and automatic earth monitoring are key to solve global-scale challenges such as disaster prevention, land use monitoring, or tackling climate change. Although there exist vast amounts of remote sensing data, most of it remains unlabeled and thus inaccessible for supervised learning algorithms. Transfer learning approaches can reduce the data requirements of deep learning algorithms. However, most of these methods are pre-trained on Ima-geNet and their generalization to remote sensing imagery is not guaranteed due to the domain gap. In this work, we propose Seasonal Contrast (SeCo), an effective pipeline to leverage unlabeled data for in-domain pre-training of remote sensing representations. The SeCo pipeline is composed of two parts. First, a principled procedure to gather large-scale, unlabeled and uncurated remote sensing datasets containing images from multiple Earth locations at different timestamps. Second, a self-supervised algorithm that takes advantage of time and position invariance to learn transferable representations for remote sensing applications. We empirically show that models trained with SeCo achieve better performance than their ImageNet pre-trained counterparts and state-of-the-art self-supervised learning methods on multiple downstream tasks. The datasets and models in SeCo will be made public to facilitate transfer learning and enable rapid progress in remote sensing applications. 1

For agents

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

get_harvested_code_for_paper("2103.16607")
get_code_for_paper("2103.16607")
have("2103.16607")

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

curl https://syntology.ai/api/ran/2103.16607.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.16607.svg)](https://syntology.ai/paper/2103.16607)

Connect an agent — have() is free.