Papers › FasterViT: Fast Vision Transformers with Hierarchical Attention

FasterViT: Fast Vision Transformers with Hierarchical Attention

9 Jun 2023arXiv:2306.06189archive 2025-07-28

Ali Hatamizadeh, Greg Heinrich, Hongxu Yin, Andrew Tao, Jose M. Alvarez, Jan Kautz, Pavlo Molchanov

We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global representation learning. At a high level, global self-attentions enable the efficient cross-window communication at lower costs. FasterViT achieves a SOTA Pareto-front in terms of accuracy and image throughput. We have extensively validated its effectiveness on various CV tasks including classification, object detection and segmentation. We also show that HAT can be used as a plug-and-play module for existing networks and enhance them. We further demonstrate significantly faster and more accurate performance than competitive counterparts for images with high resolution. Code is available at https://github.com/NVlabs/FasterViT.

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.

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

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 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: 9 samples from 1 repository, 4 ran (1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 4 samples that ran have no recorded date.

NVlabs/FasterViT officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 4 ran (3 instrument-failed) · 5 unverified report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

9 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 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
1ran
5unverified

Licence: 9 of the 9 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 NVlabs/FasterViT. “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.

NVlabs/FasterViT official repository 9 samples, 4 ran (3 instrument-failed) · 5 unverified
PosEmbMLPSwinv1D fastervit/models/faster_vit.py ran licence not identified · pointer only · 7f3339b6431dadb2 · report fixture: signature input_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
ct_dewindow fastervit/models/faster_vit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 461e5cfacd06764d · report fixture: signature ct:Tensor/6/float, W:int/0/int, H:int/0/int, window_size:int/0/int · returned Tensor · level recorded, date not recorded
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 4, kind float, dtype float32
fastervit/models/faster_vit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 7072909ab4fb3b25 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
window_reverse in 296 papers fastervit/models/faster_vit.py ran · our draft was wrong licence not identified · pointer only · 1577313e8d258159 · report fixture: signature windows:Tensor/6/float, window_size:int/0/int, H:int/0/int, W:int/0/int, B:int/0/int · returned Tensor · level recorded, date not recorded
HAT fastervit/models/faster_vit.py unverified licence not identified · pointer only · f357b45220a1fcf9 · report
Mlp in 102 papers fastervit/models/faster_vit.py unverified licence not identified · pointer only · 128ed4df18554274 · report
PosEmbMLPSwinv2D fastervit/models/faster_vit.py unverified licence not identified · pointer only · d6a720427c459fa8 · report
WindowAttention in 50 papers fastervit/models/faster_vit.py unverified licence not identified · pointer only · c8568529946c5652 · report
ct_window fastervit/models/faster_vit.py unverified licence not identified · pointer only · 808ccf2de8e71b9d · 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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Hierarchical Attention (HAT) (graph method: Hierarchical Attention (HAT)). 7 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. HAT entry · level 0 · unverified · f357b45220a1fcf9
  2. Mlp helper · level 0 · unverified · 128ed4df18554274
  3. PosEmbMLPSwinv1D helper · level 1 · ran · 7f3339b6431dadb2
  4. WindowAttention helper · level 0 · unverified · c8568529946c5652
  5. ct_dewindow helper · level 1 · ran; the contract check could not run (RAISES) · 461e5cfacd06764d
  6. ct_window helper · level 0 · unverified · 808ccf2de8e71b9d
  7. PosEmbMLPSwinv2D helper · level 0 · unverified · d6a720427c459fa8

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="2306.06189") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationObject DetectionRepresentation Learningobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet FasterViT-6 GFLOPs 142 #199 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-6 Number of params 1360M #199 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-6 Top 1 Accuracy 85.8% #199 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-5 GFLOPs 113 #217 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-5 Number of params 957.5M #217 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-5 Top 1 Accuracy 85.6% #217 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-4 GFLOPs 36.6 #235 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-4 Number of params 424.6M #235 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-4 Top 1 Accuracy 85.4% #235 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-3 GFLOPs 18.2 #282 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-3 Number of params 159.5M #282 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-3 Top 1 Accuracy 84.9% #282 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-2 GFLOPs 8.7 #340 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-2 Number of params 75.9M #340 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-2 Top 1 Accuracy 84.2% #340 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-1 GFLOPs 5.3 #459 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-1 Number of params 53.4M #459 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-1 Top 1 Accuracy 83.2% #459 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-0 GFLOPs 3.3 #578 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-0 Number of params 31.4M #578 of 1060 Archive leaderboard report
Image Classification ImageNet FasterViT-0 Top 1 Accuracy 82.1% #578 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

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