AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

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

Oscar Mañas, Alexandre Lacoste, Xavier Giró-i-Nieto, David Vazquez, Pau Rodríguez

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 397 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
sample pretraining locations around cities (Gaussian) instead of uniformly (ablation)SeCo ResNet-18 (100k) · BigEarthNet linear probing 100% labelsmAP: 72.59 -> 75.52Improved
sample pretraining locations around cities (Gaussian) instead of uniformly (ablation)SeCo ResNet-18 (100k) · BigEarthNet fine-tuning 100% labelsmAP: 85.75 -> 87.04Improved
sample pretraining locations around cities (Gaussian) instead of uniformly (ablation)SeCo ResNet-18 (100k) · BigEarthNet linear probing 10% labelsmAP: 71.63 -> 74.67Improved
add temporal positive pairs to MoCo-v2 (ablation)MoCo-v2 ResNet-18 (1M) · BigEarthNet linear probing 100% labelsmAP: 70.79 -> 73.60Improved
add temporal positive pairs to MoCo-v2 (ablation)MoCo-v2 ResNet-18 · OSCD change detectionF1: 40.71 -> 40.12No clear effect
add multiple embedding sub-spaces (SeCo) to MoCo-v2+TP (ablation)MoCo-v2+TP ResNet-18 (1M) · BigEarthNet linear probing 100% labelsmAP: 73.60 -> 77.00Improved
add multiple embedding sub-spaces (SeCo) to MoCo-v2+TP (ablation)MoCo-v2+TP ResNet-18 · OSCD change detectionF1: 40.12 -> 46.94Improved
add multiple embedding sub-spaces (SeCo) to MoCo-v2+TP (ablation)MoCo-v2+TP ResNet-18 · EuroSATaccuracy: 89.51 -> 93.14Improved
scale pretraining set from 100k to 1M images (ablation)SeCo ResNet-18 · BigEarthNet linear probing 100% labelsmAP: 75.52 -> 77.00Improved
scale pretraining set from 100k to 1M images (ablation)SeCo ResNet-50 · BigEarthNet linear probing 100% labelsmAP: 79.13 -> 80.35Improved
replace ImageNet supervised pretraining with SeCoResNet-50 · BigEarthNet fine-tuning 100% labelsmAP: 86.74 -> 87.81Improved
replace ImageNet supervised pretraining with SeCoResNet-18 · EuroSATaccuracy: 86.44 -> 93.14Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy