Physics

Pattern recognition (psychology)

Pooling

Contextual image classification

Algorithm

Image (mathematics)

Machine learning

Residual

Voltage

Artificial intelligence

Object detection

Computer science

Feature extraction

Quantum mechanics

Computer vision

Transformer

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 AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">box</sup> on COCO object detection as well as 86.1% on Kinetics-400 video classification. Code and models are available at https://github.com/facebookresearch/mvit.

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection