CoChat
Sign Up
Cited by 354Remote-Sensing Image ClassificationDomain Adaptation and Few-Shot LearningRemote Sensing and Land Use

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

Open access
Manas, Oscar, Lacoste, Alexandre, Giro-i-Nieto, Xavier, Vazquez, David, Rodriguez, Pau·2021·2021 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv48922.2021.00928
Open this paper in CoChat — free account

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 ImageNet 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

Integrity signals

Registry

Crossref · 10.1109/iccv48922.2021.00928

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The timestamp of a satellite image is useful for many pre-training or downstream vision tasks.

    “As shown in many prior works [34, 35], the timestamp of a satellite image is useful for many pre-training or downstream vision tasks.”

    From SatMAE: Pre-Training Transformers for Temporal and Multi-Spectral Satellite Imagery (2022) · cites this paper as [35]

  • Existing self-supervised learning methods for satellite imagery cannot learn general representations for both temporal and multi-spectral remote sensing data.

    “While self-supervised learning methods for satellite imagery exist [34, 35], these approaches cannot learn general representations for both temporal and multi-spectral remote sensing data.”

    From SatMAE: Pre-Training Transformers for Temporal and Multi-Spectral Satellite Imagery (2022) · cites this paper as [35]

  • GASSL and SeCo were trained on a larger pre-train dataset (1M Sentinel-2 images vs. 713k) and with all 13 bands than SatMAE's fMoW Sentinel.

    “GASSL and SeCo were actually trained on a larger pre-train dataset (1M Sentinel-2 images v.s. 713k) and with all 13 bands than our fMoW Sentinel.”

    From SatMAE: Pre-Training Transformers for Temporal and Multi-Spectral Satellite Imagery (2022) · cites this paper as [35]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Manas, O., Lacoste, A., Giro-i-Nieto, X., Vazquez, D., & Rodriguez, P.
Affiliations
  • Element AI
  • Universitat Politècnica de Catalunya
ORCID
Lacoste, Alexandre
Venue
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2021-10
Pages
9394-9403
DOI
10.1109/iccv48922.2021.00928
OpenAlex
W3144483443
Cited by
354
References
6
Citations by year
2026: 63 · 2025: 88 · 2024: 97 · 2023: 62 · 2022: 36 · 2021: 8
FWCI
81.85
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • UPCommons institutional repository (Universitat Politècnica de Catalunya) (submittedVersion, public-domain)
Topics
  • Physical Sciences › Engineering › Media Technology › Remote-Sensing Image Classification
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Remote Sensing and Land Use
Keywords
seasonal contrast, unsupervised pre-training, remote sensing images, self-supervised learning, transfer learning, unlabeled data, domain gap, time invariance, spatial invariance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review