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

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

1 Nov 2023NeurIPS 2023 11arXiv:2311.00566archive 2025-07-28

Anthony Fuller, Koreen Millard, James R. Green

A vital and rapidly growing application, remote sensing offers vast yet sparsely labeled, spatially aligned multimodal data; this makes self-supervised learning algorithms invaluable. We present CROMA: a framework that combines contrastive and reconstruction self-supervised objectives to learn rich unimodal and multimodal representations. Our method separately encodes masked-out multispectral optical and synthetic aperture radar samples -- aligned in space and time -- and performs cross-modal contrastive learning. Another encoder fuses these sensors, producing joint multimodal encodings that are used to predict the masked patches via a lightweight decoder. We show that these objectives are complementary when leveraged on spatially aligned multimodal data. We also introduce X- and 2D-ALiBi, which spatially biases our cross- and self-attention matrices. These strategies improve representations and allow our models to effectively extrapolate to images up to 17.6x larger at test-time. CROMA outperforms the current SoTA multispectral model, evaluated on: four classification benchmarks -- finetuning (avg. 1.8%), linear (avg. 2.4%) and nonlinear (avg. 1.4%) probing, kNN classification (avg. 3.5%), and K-means clustering (avg. 8.4%); and three segmentation benchmarks (avg. 6.4%). CROMA's rich, optionally multimodal representations can be widely leveraged across remote sensing applications.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.00566")

Code

Syntology Ran 11 of 23 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · violated contract; 2 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 10 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

antofuller/croma officialmentioned in papermentioned on GitHubpytorch 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.

Code Syntology ran Syntology

23 samples harvested; 11 ran; 2 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · violated contract
2ran · our draft was wrong
5ran
12unverified

Licence: 1 of the 23 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from antofuller/croma. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Attention antofuller/croma/pretrain_croma.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 1fcfdd6a3153b5d2 · report
BaseTransformer antofuller/croma/pretrain_croma.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 4e0949bd5a6c4d3a · report
ContrastLossInput antofuller/croma/pretrain_croma.py official repository ran MIT (permissive) · 9a8c2a02087bbb20 · report
CrossAttention antofuller/croma/pretrain_croma.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · ba24c9bdfa918f05 · report
FFN antofuller/croma/pretrain_croma.py official repository ran · metamorphic tier: invariant MIT (permissive) · 2346039a18d33db2 · report
apply_mask_to_alibi antofuller/croma/pretrain_croma.py official repository ran · our draft was wrong MIT (permissive) · be7db6871909bd33 · report
apply_mask_to_sequence antofuller/croma/pretrain_croma.py official repository ran · our draft was wrong MIT (permissive) · e52be538e2263534 · report
exists antofuller/CROMA/pretrain_croma.py official repository ran · violated contract MIT (permissive) · 689b78ad9d312313 · report
get_2dalibi antofuller/CROMA/use_croma.py official repository ran · honoured contract MIT (permissive) · 6861b66287490d06 · report
get_alibi antofuller/croma/pretrain_croma.py official repository ran · honoured contract MIT (permissive) · 2c3811714f31ec91 · report
BaseTransformerCrossAttn antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · d1017efaaf6dbc46 · report
CROMA antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · bfd179d5cf8b21fb · report
DecoderMAE antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · 8571409c484a1238 · report
ViT antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · 9f7fe5abf47f2d58 · report
gather_features antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · 816756cd7d531829 · report
get_1d_sincos_pos_embed_from_grid antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · 2fae31fd41fc4c69 · report
get_2d_sincos_pos_embed antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · d599b95b94498131 · report
get_2d_sincos_pos_embed antofuller/CROMA/pretrain_croma.py official repository unverified MIT (permissive) · 2ac385d924e863c5 · report
get_2d_sincos_pos_embed antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · 1b10b35db2b36f35 · report
get_2d_sincos_pos_embed_from_grid antofuller/croma/pretrain_croma.py official repository unverified MIT (permissive) · 90bcf667c7d798b4 · report
get_2d_sincos_pos_embed_from_grid antofuller/CROMA/pretrain_croma.py official repository unverified MIT (permissive) · be98aaf46e9dea53 · report
get_2dalibi antofuller/croma/use_croma.py official repository unverified MIT (permissive) · aeec3aa501ca98c5 · report
exists identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report

Tasks

Contrastive LearningDecoderSelf-Supervised Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

k-Means Clustering

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