AI Paper Atlas

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

GEO-Bench: Toward Foundation Models for Earth Monitoring

Alexandre Lacoste, Nils Lehmann, Pau Rodriguez, Evan David Sherwin, Hannah Kerner, Björn Lütjens, Jeremy Andrew Irvin, David Dao, Hamed Alemohammad, Alexandre Drouin, Mehmet Gunturkun, Gabriel Huang and 5 more

NeurIPS 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervision in supervised pipelines

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
Use ConvNeXt or SwinV2 instead of the other evaluated RGB baselinesGEO-Bench classification · GEO-Bench classification (six tasks, RGB)normalized accuracyImproved
Use ImageNet-pretrained ResNet18 instead of randomly initialized ResNet18ResNet18 · GEO-Bench classificationaccuracyImproved
Use remote-sensing-pretrained ResNet18 or ResNet50 instead of timm-pretrained weightsResNet18 and ResNet50 · GEO-Bench classification (RGB)normalized accuracyNo clear effect
Pretrain ResNet50 on Sentinel-2 multispectral data (ablation)ResNet50 · Sentinel-2 classification tasksnormalized accuracyImproved
Add randomly initialized first-layer weights for missing multispectral channels (ablation)RGB-pretrained ResNet50 and ViT-S · Sentinel-2 classification tasksnormalized accuracyNo clear effect
Use multispectral channels with ViT-S (ablation)ViT-S · Sentinel-2 classification tasksnormalized accuracyHurt
Reduce the classification training-set size (ablation)GEO-Bench classification models · GEO-Bench classificationnormalized accuracyMixed
Use ConvNeXt-B-timm with 2% of the training data instead of ResNet18-Rnd with the full training set (ablation)GEO-Bench classification · GEO-Bench classification (aggregated)normalized accuracy: 50xImproved
Use U-Net rather than DeepLabV3ResNet segmentation baselines · GEO-Bench segmentationnormalized IoUImproved
Use ResNet101 rather than ResNet50 as the segmentation backbone (ablation)U-Net and DeepLabV3 segmentation baselines · GEO-Bench segmentationnormalized IoUHurt
Reduce the training-set size (ablation)GEO-Bench classification models · GEO-Bench classificationdataset discriminativityImproved

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