XCiT: Cross-Covariance Image Transformers

by   Alaaeldin El-Nouby, et al.

Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.


page 6

page 18


Focal Self-attention for Local-Global Interactions in Vision Transformers

Recently, Vision Transformer and its variants have shown great promise o...

Vision Transformers: State of the Art and Research Challenges

Transformers have achieved great success in natural language processing....

Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse

Transformers have achieved remarkable success in several domains, rangin...

Transformer with Fourier Integral Attentions

Multi-head attention empowers the recent success of transformers, the st...

KVT: k-NN Attention for Boosting Vision Transformers

Convolutional Neural Networks (CNNs) have dominated computer vision for ...

HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction

In accelerated MRI reconstruction, the anatomy of a patient is recovered...

LambdaNetworks: Modeling Long-Range Interactions Without Attention

We present lambda layers – an alternative framework to self-attention – ...

Code Repositories


Official code Cross-Covariance Image Transformer (XCiT)

view repo