Timezone: »

XCiT: Cross-Covariance Image Transformers
Alaa El-Nouby Ali · Hugo Touvron · Mathilde Caron · Piotr Bojanowski · Matthijs Douze · Armand Joulin · Ivan Laptev · Natalia Neverova · Gabriel Synnaeve · Jakob Verbeek · Herve Jegou

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ Virtual #None

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.We will opensource our code and trained models to reproduce the reported results.

Author Information

Alaa El-Nouby Ali (Inria Paris)
Hugo Touvron (Facebook AI Research / Sorbonne University)
Mathilde Caron (INRIA)
Piotr Bojanowski (Facebook)
Matthijs Douze (Facebook AI Research)
Armand Joulin (Facebook AI research)
Ivan Laptev (INRIA)
Natalia Neverova (Facebook AI Research)
Gabriel Synnaeve (Facebook)
Jakob Verbeek (INRIA)
Herve Jegou (Facebook AI Research)

More from the Same Authors