Pith. sign in

REVIEW 7 cited by

XCiT: Cross-Covariance Image Transformers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.09681 v2 pith:YA3EYVH6 submitted 2021-06-17 cs.CV cs.LG

XCiT: Cross-Covariance Image Transformers

classification cs.CV cs.LG
keywords imagecross-covariancetransformersinteractionstokensxcitcomplexityfeature
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Representing 3D Faces with Learnable B-Spline Volumes

    cs.CV 2026-04 unverdicted novelty 7.0

    CUBE encodes 3D faces via a grid of learned high-dimensional B-spline features that map parametrically to a base shape plus MLP-refined displacements, enabling dense correspondence and state-of-the-art registration fr...

  2. Ultra-low-light computer vision using trained photon correlations

    cs.CV 2026-04 unverdicted novelty 7.0

    Trained correlated-photon illumination paired with a Transformer backend improves object classification accuracy by up to 15 percentage points in photon-starved noisy imaging.

  3. TextTeacher: What Can Language Teach About Images?

    cs.CV 2026-05 unverdicted novelty 6.0

    TextTeacher uses frozen text embeddings from captions as semantic anchors to guide vision model training, improving ImageNet accuracy by up to 2.7 p.p. and transfer performance by 1.0 p.p. on average.

  4. The Transformer as a Polar State Estimator

    cs.LG 2026-05 unverdicted novelty 6.0

    Transformer components arise as the natural solution to precision-weighted directional state estimation on the hypersphere.

  5. The Transformer as a Polar State Estimator

    cs.LG 2026-05 unverdicted novelty 6.0

    The standard Transformer block arises as a first-order approximation to a polar state estimator on the hypersphere, with a Polar Transformer retaining higher-order terms.

  6. ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching

    cs.CV 2026-04 unverdicted novelty 6.0

    ShapeY is a benchmark dataset and nearest-neighbor protocol that measures shape-based recognition in vision models, revealing that even state-of-the-art networks fail to generalize consistently across 3D viewpoints an...

  7. One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 5.0

    Non-linear transformers enable cross-domain generalization in in-context RL by representing value functions from different domains with shared weights inside a shared RKHS.