AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

Adam J Stewart, Nils Lehmann, Isaac Corley, Yi Wang, Yi-Chia Chang, Nassim Ait Ait Ali Braham, Shradha Sehgal, Caleb Robinson, Arindam Banerjee

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 6 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
replace ImageNet pretraining with SSL4EO-L MoCoViT-S16 · L7 Irish cloud detectionaccuracy: 68.22 -> 86.65Improved
replace ImageNet pretraining with SSL4EO-L MoCoViT-S16 · L7 Irish cloud detectionmIoU: 51.78 -> 76.03Improved
replace ImageNet pretraining with SSL4EO-L SimCLRViT-S16 · L7 Irish cloud detectionmIoU: 51.78 -> 70.47Improved
replace ImageNet pretraining with SSL4EO-L SimCLRResNet-18 · L7 Irish cloud detectionaccuracy: 64.08 -> 34.80Hurt
replace ImageNet pretraining with SSL4EO-L MoCoResNet-18 · L8 Biome cloud detectionmIoU: 24.67 -> 27.33Improved
replace ImageNet pretraining with SSL4EO-L MoCoViT-S16 · L8 Biome cloud detectionmIoU: 30.98 -> 30.33Hurt
replace ImageNet pretraining with SSL4EO-L SimCLRAll backbones · Cloud detection (L7 Irish, L8 Biome)accuracy/mIoU: 2 out of 6Mixed
replace ImageNet pretraining with SSL4EO-L MoCoAll backbones · NLCD and CDL land coveraccuracy/mIoU: 25 out of 30Improved
replace ImageNet pretraining with SSL4EO-L MoCoResNet-50 · NLCD, Landsat 4-5 TM TOAmIoU: 49.96 -> 53.28Improved
replace ImageNet pretraining with SSL4EO-L MoCoResNet-50 · CDL, Landsat 7 ETM+ TOAmIoU: 49.51 -> 47.19Hurt
replace ImageNet pretraining with SSL4EO-L SimCLRAll backbones · NLCD and CDL land coveraccuracy/mIoU: 24 out of 30Hurt
use SSL4EO-L MoCo gains on land cover (best case)All backbones · NLCD and CDL land coveraccuracy/mIoU: 6.60% overall accuracy and 7.13 mIoUImproved

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