# MViT V2¶

## Abstract¶

In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative positional embeddings and residual pooling connections. We instantiate this architecture in five sizes and evaluate it for ImageNet classification, COCO detection and Kinetics video recognition where it outperforms prior work. We further compare MViTv2s’ pooling attention to window attention mechanisms where it outperforms the latter in accuracy/compute. Without bells-and-whistles, MViTv2 has state-of-the-art performance in 3 domains: 88.8% accuracy on ImageNet classification, 58.7 boxAP on COCO object detection as well as 86.1% on Kinetics-400 video classification.

## Results and models¶

### ImageNet-1k¶

Model

Pretrain

Params(M)

Flops(G)

Top-1 (%)

Top-5 (%)

Config

MViTv2-tiny*

From scratch

24.17

4.70

82.33

96.15

config

model

MViTv2-small*

From scratch

34.87

7.00

83.63

96.51

config

model

MViTv2-base*

From scratch

51.47

10.20

84.34

96.86

config

model

MViTv2-large*

From scratch

217.99

42.10

85.25

97.14

config

model

Models with * are converted from the official repo. The config files of these models are only for inference. We don’t ensure these config files’ training accuracy and welcome you to contribute your reproduction results.

## Citation¶

@inproceedings{li2021improved,
title={MViTv2: Improved multiscale vision transformers for classification and detection},
author={Li, Yanghao and Wu, Chao-Yuan and Fan, Haoqi and Mangalam, Karttikeya and Xiong, Bo and Malik, Jitendra and Feichtenhofer, Christoph},
booktitle={CVPR},
year={2022}
}