Methods › General › Attention Mechanisms › Cross-Covariance Attention

Cross-Covariance Attention

7 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Cross-Covariance Attention, or XCA, is an attention mechanism which operates along the feature dimension instead of the token dimension as in conventional transformers.

Using the definitions of queries, keys and values from conventional attention, the cross-covariance attention function is defined as:

XC-Attention (Q, K, V)=V 𝒜_(XC)(K, Q), 𝒜_(XC)(K, Q)=Softmax(K̂^⊤ Q̂ / τ)

where each output token embedding is a convex combination of the dᵥ features of its corresponding token embedding in V. The attention weights 𝒜 are computed based on the cross-covariance matrix.

Source: XCiT: Cross-Covariance Image Transformers

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Dual Cross Attention; Cross Segment Attention; Rolling Cross-Attention; reverse cross-attention; Dual Cross-Attention (DCA); Tree Cross Attention (TCA); Gated Cross-Modal Attention; Energy-Based Cross Attention.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 7 · with a code link: 5 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 7 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 7 of 7, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Classification3
image-classification2
Decoder1
Deformable Medical Image Registration1
Denoising1
Image Registration1
Instance Segmentation1
Medical Image Analysis1
Medical Image Registration1
Motion Magnification1
Object Detection1
Pose Estimation1
Quantization1
Self-Supervised Image Classification1
Semantic Segmentation1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with Cross-Covariance Attention: 2021 to 2024, peak 2 2 0 2021: 2 papers 2021 2022: 2 papers 2022 2023: 1 paper 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (7 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Attention Mechanisms

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections