Papers › Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test...

Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation

26 May 2024arXiv:2405.16486archive 2025-07-28

Rongyu Zhang, Aosong Cheng, Yulin Luo, Gaole Dai, Huanrui Yang, Jiaming Liu, ran Xu, Li Du, Yuan Du, Yanbing Jiang, Shanghang Zhang

Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture, continuously adapting the model from one domain distribution to another can result in serious catastrophic forgetting. Drawing inspiration from the human visual system's adeptness at processing both shape and texture according to the famous Trichromatic Theory, we explore the integration of a Mixture-of-Activation-Sparsity-Experts (MoASE) as an adapter for the CTTA task. Given the distinct reaction of neurons with low/high activation to domain-specific/agnostic features, MoASE decomposes the neural activation into high-activation and low-activation components with a non-differentiable Spatial Differentiate Dropout (SDD). Based on the decomposition, we devise a multi-gate structure comprising a Domain-Aware Gate (DAG) that utilizes domain information to adaptive combine experts that process the post-SDD sparse activations of different strengths, and the Activation Sparsity Gate (ASG) that adaptively assigned feature selection threshold of the SDD for different experts for more precise feature decomposition. Finally, we introduce a Homeostatic-Proximal (HP) loss to bypass the error accumulation problem when continuously adapting the model. Extensive experiments on four prominent benchmarks substantiate that our methodology achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Our code is now available at https://github.com/RoyZry98/MoASE-Pytorch.

PaperPDFCodeCode Syntology ran

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.

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

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 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: official repository: 15 samples from 1 repository, 12 ran (5 with no instrument failure; 7 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

royzry98/moase-pytorch officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 12 ran (7 instrument-failed) · 3 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
4ran; the contract check could not run
3ran
3unverified

Licence: 15 of the 15 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 royzry98/moase-pytorch. “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”. “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.

royzry98/moase-pytorch official repository 15 samples, 12 ran (7 instrument-failed) · 3 unverified
boolean_string in 17 papers utils.py ran · violated contract no licence file found · pointer only · b1f9cebf0d177140 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-22
collect_stats norm.py ran · our draft was wrong no licence file found · pointer only · c5f915703f30ab89 · report fixture: signature model:callable/0/? · returned tuple · level recorded 2026-09-24
configure_model in 14 papers norm.py ran no licence file found · pointer only · 8f537ee8d4a9b397 · report fixture: signature model:callable/0/?, eps:float/0/float, momentum:float/0/float, reset_stats:bool/0/bool, no_stats:bool/0/bool · returned Sequential · level recorded 2026-09-24
convert_tensor_to_image utils.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 18b41dffa7b33f34 · report fixture: signature x:ndarray/4/float · returned ndarray · level recorded 2026-09-24
make_custom_dataset in 7 papers robustbench/loaders.py ran no licence file found · pointer only · 4aedf5bc9100546f · report fixture: signature root:str/0/str, path_imgs:str/0/str, cls_dict:str/0/str · returned list · level recorded 2026-09-24
param_augment cotta_vit_opd.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 660527f45da7af3b · report fixture: signature x:Tensor/4/float, a:Tensor/2/float, img_size:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-24
pil_loader in 144 papers robustbench/loaders.py ran · honoured contract no licence file found · pointer only · f321f54723433661 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22
pytorch_evaluate utils.py ran no licence file found · pointer only · 02d40fa8eb9d95d7 · report fixture: signature net:callable/0/?, data_loader:DataLoader/0/?, fetch_keys:list/1/str, x_shape:NoneType/0/?, output_shapes:dict/0/?, to_tensor:bool/0/bool, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
reverse_kl in 5 papers cotta_vit_opd.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 6bc4cd7ae8f4b04d · report fixture: signature student_logits:Tensor/2/float, teacher_logits:Tensor/2/float, T:float/0/float · returned Tensor · level recorded 2026-09-24
setup_source in 6 papers cifar100c_vit.py ran · our draft was wrong no licence file found · pointer only · 721e565ebd5fda4e · report fixture: signature model:callable/0/? · returned MinimalModel · level recorded 2026-09-22
softmax_entropy in 54 papers
census: 18 implementations from 29 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
cotta_vit.py ran; the contract check could not run (RAISES) no licence file found · pointer only · e589e47d748af885 · report fixture: returned Tensor · level recorded 2026-09-26
update_ema_variables in 17 papers cotta_vit.py ran · our draft was wrong no licence file found · pointer only · a77d556c0aea19c1 · report fixture: signature ema_model:callable/0/?, model:callable/0/?, alpha_teacher:float/0/float · returned SimpleModel · level recorded 2026-09-22
accimage_loader in 47 papers robustbench/loaders.py unverified no licence file found · pointer only · 404fb2b2daa1ae78 · report
load_cifar10 in 20 papers robustbench/data.py unverified no licence file found · pointer only · 2ef65c34f0fa8042 · report
load_cifar100 in 6 papers robustbench/data.py unverified no licence file found · pointer only · 52acd5b81cee97b1 · report

Tasks

Mixture-of-ExpertsTest-time Adaptationfeature selection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterDropoutFeature Selection

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