Methods › Computer Vision › Vision Transformers › MViT
Multiscale Vision Transformer
MViT
Introduced by Haoqi Fan et al. in Multiscale Vision Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Multiscale Vision Transformer, or MViT, is a transformer architecture for modeling visual data such as images and videos. Unlike conventional transformers, which maintain a constant channel capacity and resolution throughout the network, Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 8 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Multiscale Vision Transformers (MViT)' (resolution: alias); this answer is about that name. This answer is about arXiv:2104.11227, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2104.11227 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified (of 26 harvested samples) · 5 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 9 · with a code link: 5 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 9 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 9 of 9, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
ROI-Aware Multiscale Cross-Attention Vision Transformer for Pest Image Identification 28 Dec 2023 · 0 repositories · arXiv:2312.16914
-
PaReprop: Fast Parallelized Reversible Backpropagation 15 Jun 2023 · 1 repository · arXiv:2306.09342
-
SVT: Supertoken Video Transformer for Efficient Video Understanding 1 Apr 2023 · 0 repositories · arXiv:2304.00325
-
Multi-Channel Vision Transformer for Epileptic Seizure Prediction 29 Jun 2022 · 0 repositories
-
Benchmarking Conventional Vision Models on Neuromorphic Fall Detection and Action Recognition Dataset 28 Jan 2022 · 0 repositories · arXiv:2201.12285
-
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection 2 Dec 2021 · 9 repositories · arXiv:2112.01526
-
Efficient Video Transformers with Spatial-Temporal Token Selection 23 Nov 2021 · 1 repository · arXiv:2111.11591
-
Class-agnostic Object Detection with Multi-modal Transformer 22 Nov 2021 · 1 repository · arXiv:2111.11430
-
Multiscale Vision Transformers 22 Apr 2021 · 8 repositories · arXiv:2104.11227Syntology community repositories only · 13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified (of 26 harvested samples) · 5 pointer-only (licence)
Tasks archive 2025-07-28
20 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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