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.
Papers archive 2025-07-28
9 shown of 9, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
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 ran 13 of 26 samples · 13 unverified · 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