Papers › Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers

Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers

26 May 2024arXiv:2405.16419archive 2025-07-28

Chau Pham, Bryan A. Plummer

Multi-Channel Imaging (MCI) contains an array of challenges for encoding useful feature representations not present in traditional images. For example, images from two different satellites may both contain RGB channels, but the remaining channels can be different for each imaging source. Thus, MCI models must support a variety of channel configurations at test time. Recent work has extended traditional visual encoders for MCI, such as Vision Transformers (ViT), by supplementing pixel information with an encoding representing the channel configuration. However, these methods treat each channel equally, i.e., they do not consider the unique properties of each channel type, which can result in needless and potentially harmful redundancies in the learned features. For example, if RGB channels are always present, the other channels can focus on extracting information that cannot be captured by the RGB channels. To this end, we propose DiChaViT, which aims to enhance the diversity in the learned features of MCI-ViT models. This is achieved through a novel channel sampling strategy that encourages the selection of more distinct channel sets for training. Additionally, we employ regularization and initialization techniques to increase the likelihood that new information is learned from each channel. Many of our improvements are architecture agnostic and can be incorporated into new architectures as they are developed. Experiments on both satellite and cell microscopy datasets, CHAMMI, JUMP-CP, and So2Sat, report DiChaViT yields a 1.5 - 5.0% gain over the state-of-the-art. Our code is publicly available at https://github.com/chaudatascience/diverse_channel_vit.

PaperPDFCodeCode 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 DiChaViT, generated from the paper text (not the authors' code), at level 3 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)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='DiChaViT') (how to connect); the free check have('2405.16419') needs no token.

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

Code

Syntology 22 code samples harvested from 1 repository linked to this paper: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 8 ran (5 with no instrument failure; 3 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/diverse_channel_vit officialmentioned in papermentioned on GitHubpytorchSyntology: 22 samples, 8 ran (3 instrument-failed) · 14 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

22 samples harvested: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 14 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
2ran; the contract check could not run
5ran
14unverified

Licence: 0 of the 22 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/diverse_channel_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 2 samples 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/diverse_channel_vit official repository 22 samples, 8 ran (3 instrument-failed) · 14 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/dichavit.py ran MIT (permissive) · b02da06042eb84e7 · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/dichavit.py ran MIT (permissive) · efa81f6f1800c5f2 · report fixture: returned Block · 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/dichavit.py ran fingerprinted MIT (permissive) · 07bed269ee55adea · report fixture: returned DropPath · level recorded 2026-09-22
PPTAttention models/dichavit.py ran MIT (permissive) · 3783c6d21458155a · report fixture: returned PPTAttention · level recorded 2026-09-22
PatchEmbedPerChannel models/dichavit.py ran MIT (permissive) · b7c9a06a56b29150 · report fixture: returned PatchEmbedPerChannel · level recorded 2026-09-22
_no_grad_trunc_normal_ in 16 papers
census: 16 implementations from 16 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/dichavit.py ran; the contract check could not run (RAISES) MIT (permissive) · d05e018c317ed42b · 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
repeat in 22 papers models/dichavit.py ran · our draft was wrong MIT (permissive) · 6a1004bd6c0e8713 · report fixture: signature _func:callable/0/?, num_times:int/0/int · returned function · 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/dichavit.py ran; the contract check could not run (RAISES) MIT (permissive) · be2feea89481c009 · 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
BlockV2 models/dichavit.py unverified MIT (permissive) · b74c375dce9be992 · report
ChannelPoolingType models/dichavit.py unverified MIT (permissive) · 850df2d33a40aa5c · report
ChannelVisionTransformer models/dichavit.py unverified MIT (permissive) · 9d61daea5bd82f74 · report
DiChaViT models/dichavit.py unverified MIT (permissive) · 79d83c31c74cf9eb · report
ExtendedEnum models/dichavit.py unverified MIT (permissive) · 7cee5c49462dff95 · report
FeaturePooling models/dichavit.py unverified MIT (permissive) · ac6302bb71f99f90 · report
FirstLayerInit models/dichavit.py unverified MIT (permissive) · b090579be5b89e33 · report
Model in 227 papers models/dichavit.py unverified MIT (permissive) · 272b7996ff94b551 · report
NewChannelLeaveOneOut models/dichavit.py unverified MIT (permissive) · 77136f4a6e0aa8ad · report
NormType models/dichavit.py unverified MIT (permissive) · f2d5816c2118046f · report
channelvit_base models/dichavit.py unverified MIT (permissive) · ee0353477276e1bc · report
channelvit_distill models/dichavit.py unverified MIT (permissive) · 56cf5bca49d77894 · report
channelvit_small models/dichavit.py unverified MIT (permissive) · 647608ff217cae3b · report
channelvit_tiny models/dichavit.py unverified MIT (permissive) · 4cd84952d4978056 · 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 DiChaViT (graph method: DiChaViT), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 6 property tests passed on both).

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

  1. compute_diversity_sampling_probabilities entry · level 3 · ran · honoured contract · c2fa915ee83d9500f88067bb327c588fe64e2918a6148f5e7f5d68c12aa1b0ff

harvested Assembly for DiChaViT (graph method: DiChaViT). 24 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

  1. DiChaViT entry · level 0 · unverified · 79d83c31c74cf9eb
  2. Model helper · level 0 · unverified · 272b7996ff94b551
  3. NewChannelLeaveOneOut helper · level 0 · unverified · 77136f4a6e0aa8ad
  4. channelvit_base helper · level 0 · unverified · ee0353477276e1bc
  5. channelvit_distill helper · level 0 · unverified · 56cf5bca49d77894
  6. channelvit_small helper · level 0 · unverified · 647608ff217cae3b
  7. channelvit_tiny helper · level 0 · unverified · 4cd84952d4978056
  8. ChannelPoolingType helper · level 0 · unverified · 850df2d33a40aa5c
  9. FeaturePooling helper · level 0 · unverified · ac6302bb71f99f90
  10. FirstLayerInit helper · level 0 · unverified · b090579be5b89e33
  11. NormType helper · level 0 · unverified · f2d5816c2118046f
  12. ExtendedEnum helper · level 0 · unverified · 7cee5c49462dff95
  13. ChannelVisionTransformer model · level 0 · unverified · 9d61daea5bd82f74
  14. Block helper · level 1 · ran · efa81f6f1800c5f2
  15. BlockV2 helper · level 0 · unverified · b74c375dce9be992
  16. PatchEmbedPerChannel model · level 1 · ran · b7c9a06a56b29150
  17. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · be2feea89481c009
  18. Attention helper · level 1 · ran · b02da06042eb84e7
  19. DropPath helper · level 1 · ran · 07bed269ee55adea
  20. Mlp helper · level 1 · ran · 86db5e5160400425
  21. drop_path helper · level 1 · ran; the contract check could not run · 55120f2026b56aa2
  22. PPTAttention helper · level 1 · ran · 3783c6d21458155a
  23. repeat helper · level 1 · ran · our draft was wrong · 6a1004bd6c0e8713
  24. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · d05e018c317ed42b

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="2405.16419") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Diversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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