AI Paper Atlas

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

CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders

Anthony Fuller, Koreen Millard, James R Green

NeurIPS 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 32 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
combine contrastive and MAE objectives (vs MAE only) (ablation)CROMA-B · BigEarthNet optical linear probemAP: -6.0 change when removing contrastiveImproved
combine contrastive and MAE objectives (vs contrast only) (ablation)CROMA-B · BigEarthNet optical linear probemAP: -3.0 change when removing MAEImproved
2D-ALiBi + X-ALiBi instead of 2D-sinusoidal (ablation)CROMA-B · segmentation avgmIoU: -1.7 when using sinusoidalImproved
2D-ALiBi instead of PEG (ablation)CROMA-B · segmentation avgmIoU: -0.7 when using PEGImproved
add X-ALiBi on top of 2D-ALiBi (ablation)CROMA-B · avg across six evalsmAP/mIoU: -0.2 without X-ALiBiImproved
2D-ALiBi for extrapolation to 504x504 images (ablation)CROMA-B · DW-Expert-120mIoU: 19.5 -> 58.8Improved
lower mask ratio (independent 50% vs 75%) (ablation)CROMA-B · avg ablationmIoU: +0.1No clear effect
multimodal MAE target instead of radar-only (ablation)CROMA-B · segmentation avgmIoU: -0.5 with radar-onlyImproved
larger MAE decoder (depth 6, dim 768) (ablation)CROMA-B · segmentation avgmIoU: +0.1No clear effect
scale to 300 epochs pretraining (ablation)CROMA-B · segmentation avgmIoU: +1.0Improved
add radar-optical joint representation vs optical onlyCROMA · BigEarthNet linear probemAP: +1.2Improved
fMoW-Sentinel finetuning vs SatMAECROMA-B · fMoW-Sentinel finetuningTop-1: 57.20 -> 54.47Hurt

Later papers that compared with this method

2 later accepted papers report CROMA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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