Papers › SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised...

SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation

13 Nov 2022arXiv:2211.07044archive 2025-07-28

Yi Wang, Nassim Ait Ali Braham, Zhitong Xiong, Chenying Liu, Conrad M Albrecht, Xiao Xiang Zhu

Self-supervised pre-training bears potential to generate expressive representations without human annotation. Most pre-training in Earth observation (EO) are based on ImageNet or medium-size, labeled remote sensing (RS) datasets. We share an unlabeled RS dataset SSL4EO-S12 (Self-Supervised Learning for Earth Observation - Sentinel-1/2) to assemble a large-scale, global, multimodal, and multi-seasonal corpus of satellite imagery from the ESA Sentinel-1 & -2 satellite missions. For EO applications we demonstrate SSL4EO-S12 to succeed in self-supervised pre-training for a set of methods: MoCo-v2, DINO, MAE, and data2vec. Resulting models yield downstream performance close to, or surpassing accuracy measures of supervised learning. In addition, pre-training on SSL4EO-S12 excels compared to existing datasets. We make openly available the dataset, related source code, and pre-trained models at https://github.com/zhu-xlab/SSL4EO-S12.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

zhu-xlab/ssl4eo-s12 officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SSL4EO-L: Datasets and Foundation Models for Landsat Imagery (arXiv:2306.09424; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zhu-xlab/dino-mm mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decoupling Common and Unique Representations for Multimodal Self-supervised Learning (arXiv:2309.05300; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zhu-xlab/softcon mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
zhu-xlab/ssl4eo-review mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Earth ObservationMulti-Label Image ClassificationSelf-Supervised Learning

Datasets

Introduced by this paper, per the archive.

SSL4EO-S12

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Image Classification BigEarthNet MoCo-v2 (ResNet50, fine tune) mAP (micro) 91.8 #1 of 10 Archive leaderboard report
Multi-Label Image Classification BigEarthNet MoCo-v2 (ResNet50, fine tune) official split No #1 of 10 Archive leaderboard report
Multi-Label Image Classification BigEarthNet MoCo-v3 (ViT-S/16, fine tune) mAP (micro) 89.9 #2 of 10 Archive leaderboard report
Multi-Label Image Classification BigEarthNet MoCo-v3 (ViT-S/16, fine tune) official split No #2 of 10 Archive leaderboard report
Multi-Label Image Classification BigEarthNet MAE (ViT-S/16, fine tune) mAP (micro) 88.9 #4 of 10 Archive leaderboard report
Multi-Label Image Classification BigEarthNet MAE (ViT-S/16, fine tune) official split No #4 of 10 Archive leaderboard report
Multi-Label Image Classification BigEarthNet (official test set) MoCov3 (ViT-S/16) F1 Score 80.5 #2 of 6 Archive leaderboard report
Multi-Label Image Classification BigEarthNet (official test set) MoCov3 (ViT-S/16) mAP (micro) 89.3 #2 of 6 Archive leaderboard report
Multi-Label Image Classification BigEarthNet (official test set) MoCov2 (ResNet50) F1 Score 79.8 #3 of 6 Archive leaderboard report
Multi-Label Image Classification BigEarthNet (official test set) MoCov2 (ResNet50) mAP (micro) 88.7 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMAEMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections