Papers › ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision...

ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning

25 Mar 2025arXiv:2503.19331archive 2025-07-28

Chau Pham, Juan C. Caicedo, Bryan A. Plummer

Prior work using Masked Autoencoders (MAEs) typically relies on random patch masking based on the assumption that images have significant redundancies across different channels, allowing for the reconstruction of masked content using cross-channel correlations. However, this assumption does not hold in Multi-Channel Imaging (MCI), where channels may provide complementary information with minimal feature overlap. Thus, these MAEs primarily learn local structures within individual channels from patch reconstruction, failing to fully leverage cross-channel interactions and limiting their MCI effectiveness. In this paper, we present ChA-MAEViT, an MAE-based method that enhances feature learning across MCI channels via four key strategies: (1) dynamic channel-patch masking, which compels the model to reconstruct missing channels in addition to masked patches, thereby enhancing cross-channel dependencies and improving robustness to varying channel configurations; (2) memory tokens, which serve as long-term memory aids to promote information sharing across channels, addressing the challenges of reconstructing structurally diverse channels; (3) hybrid token fusion module, which merges fine-grained patch tokens with a global class token to capture richer representations; and (4) Channel-Aware Decoder, a lightweight decoder utilizes channel tokens to effectively reconstruct image patches. Experiments on satellite and microscopy datasets, CHAMMI, JUMP-CP, and So2Sat, show that ChA-MAEViT significantly outperforms state-of-the-art MCI-ViTs by 3.0-21.5%, highlighting the importance of cross-channel interactions in MCI.

PaperPDFCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

Syntology holds a reference implementation of ChA-MAEViT, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='ChA-MAEViT') (how to connect); the free check have('2503.19331') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 16 samples from 1 repository, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chaudatascience/cha_mae_vit found in paper text by SyntologySyntology: 16 samples, 12 ran (5 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
4ran; the contract check could not run
7ran
4unverified

Licence: 0 of the 16 samples are 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 chaudatascience/cha_mae_vit. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

chaudatascience/cha_mae_vit found in paper text by Syntology 16 samples, 12 ran (5 instrument-failed) · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/cha_mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · f52cc7c3cf1e75b2 · report fixture: returned Attention · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
models/cha_mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 4d93211cfa9bdffc · report fixture: returned DropPath · level recorded 2026-09-22
FourierLoss models/cha_mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 2c08d4163d35c3c0 · report fixture: returned FourierLoss · level recorded 2026-09-22
LayerScale in 15 papers models/cha_mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · dadddc177deadf88 · report fixture: returned LayerScale · level recorded 2026-09-22
MAB in 12 papers models/cha_mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · ca81184e1a038ae8 · report fixture: returned MAB · level recorded 2026-09-22
MemEffAttentionV2 models/cha_mae_vit.py ran fingerprinted MIT (permissive) · 0519949718350286 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
PatchEmbedPerChannel models/cha_mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · f6cefe6ba63d87f4 · report fixture: returned PatchEmbedPerChannel · level recorded 2026-09-22
compute_proxy_loss models/cha_mae_vit.py ran · our draft was wrong MIT (permissive) · fb7b61cc6dba0670 · report fixture: signature proxies:Tensor/2/float, img_emb:Tensor/2/float, gt_imgs:Tensor/1/int, scale:Tensor/0/float · returned Tensor · level recorded 2026-09-22
maybe_flatten_images models/cha_mae_vit.py ran; the contract check could not run (RAISES) MIT (permissive) · d2d59e7a9a1b0c98 · report fixture: signature img:Tensor/4/float, patch_size:int/0/int, channel_agnostic:bool/0/bool · returned Tensor · level recorded 2026-09-22
ortho_proj_loss_fn_v2 models/cha_mae_vit.py ran; the contract check could not run (RAISES) MIT (permissive) · 62ec9cace7925686 · report fixture: signature features:Tensor/3/float, labels:Tensor/1/int, gamma_s:float/0/float, gamma_d:float/0/float, reverse_pos_pairs:bool/0/bool, use_square:bool/0/bool, patch_mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
pairwise_distance_v2 models/cha_mae_vit.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 922f4bf4c1f8faa4 · report fixture: signature proxies:Tensor/2/float, x:Tensor/2/float, squared:bool/0/bool · returned Tensor · level recorded 2026-09-22
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/cha_mae_vit.py ran; the contract check could not run (RAISES) MIT (permissive) · fabe0899316ffaa5 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
ChAMAEViT models/cha_mae_vit.py unverified MIT (permissive) · e3ff5832339c1afa · report
ChAMAEViTDecoder models/cha_mae_vit.py unverified MIT (permissive) · ae881416a26c08eb · report
MemEffAttention models/cha_mae_vit.py unverified MIT (permissive) · 80fb55fa0569e3d0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for ChA-MAEViT (graph method: ChA-MAEViT), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. generate_cha_mae_mask entry · level 2 · ran · 5b65fd2b6313a25f6a98d8b2c68245c2cc02489d140b3c32b95f0134388c9779

harvested Assembly for ChA-MAEViT (graph method: ChA-MAEViT). 20 bricks; individually on a fixture: 16 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. ChAMAEViT entry · level 0 · unverified · e3ff5832339c1afa
  2. Block helper · level 0 · unverified · 46297c90ff2f0ed7
  3. ChAMAEViTDecoder model · level 0 · unverified · ae881416a26c08eb
  4. FourierLoss helper · level 1 · ran · 2c08d4163d35c3c0
  5. MAB helper · level 1 · ran · ca81184e1a038ae8
  6. PatchEmbedPerChannel model · level 1 · ran · f6cefe6ba63d87f4
  7. compute_proxy_loss helper · level 1 · ran · our draft was wrong · fb7b61cc6dba0670
  8. maybe_flatten_images helper · level 1 · ran; the contract check could not run (RAISES) · d2d59e7a9a1b0c98
  9. ortho_proj_loss_fn_v2 helper · level 1 · ran; the contract check could not run (RAISES) · 62ec9cace7925686
  10. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · fabe0899316ffaa5
  11. Attention helper · level 1 · ran · f52cc7c3cf1e75b2
  12. DropPath helper · level 1 · ran · 4d93211cfa9bdffc
  13. LayerScale helper · level 1 · ran · dadddc177deadf88
  14. MemEffAttention helper · level 0 · unverified · 80fb55fa0569e3d0
  15. MemEffAttentionV2 helper · level 1 · ran · 0519949718350286
  16. Mlp helper · level 1 · ran · a1715055832f71fd
  17. drop_path helper · level 1 · ran; the contract check could not run · 55120f2026b56aa2
  18. pairwise_distance_v2 helper · level 1 · ran; the contract check could not run (RAISES) · 922f4bf4c1f8faa4
  19. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 813ed3a96c17cf42
  20. exists helper · level 1 · ran · violated contract · aa5486a3650902d8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2503.19331") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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