Papers › CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient...

CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications

7 Aug 2024arXiv:2408.03703archive 2025-07-28

Tianfang Zhang, Lei LI, Yang Zhou, Wentao Liu, Chen Qian, Jenq-Neng Hwang, Xiangyang Ji

Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on resource-constrained scenarios and real-time applications, such as mobile devices, although considerable efforts have been made in previous works. In this paper, we introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications. Firstly, we argue that the capability of token mixers to obtain global contextual information hinges on multiple information interactions, such as spatial and channel domains. Subsequently, we propose Convolutional Additive Token Mixer (CATM) employing underlying spatial and channel attention as novel interaction forms. This module eliminates troublesome complex operations such as matrix multiplication and Softmax. We introduce Convolutional Additive Self-attention(CAS) block hybrid architecture and utilize CATM for each block. And further, we build a family of lightweight networks, which can be easily extended to various downstream tasks. Finally, we evaluate CAS-ViT across a variety of vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation. Our M and T model achieves 83.0%/84.1% top-1 with only 12M/21M parameters on ImageNet-1K. Meanwhile, throughput evaluations on GPUs, ONNX, and iPhones also demonstrate superior results compared to other state-of-the-art backbones. Extensive experiments demonstrate that our approach achieves a better balance of performance, efficient inference and easy-to-deploy. Our code and model are available at: https://github.com/Tianfang-Zhang/CAS-ViT

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 6 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (5 with no instrument failure; 1 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 6 samples that ran have no recorded date.

tianfang-zhang/cas-vit officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (1 instrument-failed) · 0 unverified report
gitlab.com/birder/birder pytorchSyntology: not harvested 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 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.

3ran · honoured contract
1ran · our draft was wrong
2ran

Licence: 3 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tianfang-zhang/cas-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”. “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.

tianfang-zhang/cas-vit official repository 6 samples, 6 ran (1 instrument-failed) · 0 unverified
Stage classification/model/rcvit.py ran MIT (permissive) · a4cb506c560f097d · report fixture: signature dim:int/0/int, index:int/0/int, layers:list/1/int, mlp_ratio:float/0/float, act_layer:callable/0/?, attn_bias:bool/0/bool, drop:float/0/float, drop_path_rate:float/0/float · returned Sequential · level recorded 2026-09-24
cosine_scheduler in 74 papers classification/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · b700fb0a3496b255 · report fixture: signature base_value:float/0/float, final_value:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int, warmup_epochs:int/0/int, start_warmup_value:float/0/float, warmup_steps:int/0/int · returned ndarray · level recorded 2026-09-25
count_parameters in 278 papers classification/model/rcvit.py ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
get_num_layer_for_convnext in 13 papers classification/optim_factory.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 199223de2f9704cf · report fixture: signature var_name:str/0/str · returned int · level recorded 2026-09-25
get_parameter_groups in 30 papers classification/optim_factory.py ran MIT (permissive) · 979fc7d0ba424da1 · report fixture: signature model:callable/0/?, weight_decay:float/0/float, skip_list:tuple/1/empty, get_num_layer:callable/0/?, get_layer_scale:callable/0/? · returned list · level recorded 2026-09-24
stem in 11 papers classification/model/rcvit.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · b72ba06382340c08 · report fixture: signature in_chs:int/0/int, out_chs:int/0/int · returned Sequential · level recorded, date not recorded

Tasks

Image ClassificationInstance SegmentationObject DetectionSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet CAS-ViT-T GFLOPs 3.597 #352 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-T Number of params 21.76M #352 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-T Top 1 Accuracy 84.1% #352 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-M GFLOPs 1.887 #475 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-M Number of params 12.42M #475 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-M Top 1 Accuracy 83.0% #475 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-S GFLOPs 0.932 #662 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-S Number of params 5.76M #662 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-S Top 1 Accuracy 81.1% #662 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-XS GFLOPs 0.56 #811 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-XS Number of params 3.2M #811 of 1060 Archive leaderboard report
Image Classification ImageNet CAS-ViT-XS Top 1 Accuracy 78.7% #811 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionSoftmax

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