AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

A Gyrovector Space Approach for Symmetric Positive Semi-Definite Matrix Learning

Xuan Son Nguyen

ECCV 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: Geometry of low-rank and SPD structure · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use full-rank instead of low-rank learning (p=14) (ablation)SPSD-AI · HDM05accuracy (%): 74.19 -> 81.32Improved
use full-rank instead of low-rank learning (p=14) (ablation)SPSD-AI · NTU60 interaction (X-Sub)accuracy (%): 89.78 -> 95.86Improved
use full-rank instead of low-rank learning (ablation)SPSD-AI · HDM05training time per epoch (min): 0.66 -> 1.09Hurt
use full-rank instead of low-rank learning (ablation)SPSD-AI · NTU60 interaction (X-Sub)training time per epoch (min): 5.61 -> 9.19Hurt
add canonical representation in low-rank SPSD layer (ablation)SPSD-AI low-rank · HDM05accuracy (%): 41.37 -> 74.19Improved
add canonical representation in low-rank SPSD layer (ablation)SPSD-AI low-rank · FPHAaccuracy (%): 63.41 -> 90.94Improved
add canonical representation in low-rank SPSD layer (ablation)SPSD-AI low-rank · NTU60 interaction (X-Sub)accuracy (%): 56.82 -> 89.78Improved
add canonical representation in low-rank SPSD layer (ablation)SPSD-AI low-rank · NTU60 interaction (X-View)accuracy (%): 58.34 -> 90.15Improved
use Affine-invariant geometry instead of Log-EuclideanSPSD networks · HDM05accuracy (%): 77.46 -> 81.32Improved
use Affine-invariant geometry instead of Log-CholeskySPSD networks · HDM05accuracy (%): 73.52 -> 81.32Improved
use Affine-invariant geometry instead of Log-EuclideanSPSD networks · NTU60 interaction (X-Sub)accuracy (%): 90.74 -> 95.86Improved
use Affine-invariant geometry instead of Log-CholeskySPSD networks · FPHAaccuracy (%): 89.73 -> 96.58Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy