AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Persistence Paths and Signature Features in Topological Data Analysis

Ilya Chevyrev, Vidit Nanda, Harald Oberhauser

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory

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 Betti embedding in feature form instead of sliced Wasserstein kernelk_SW · Shapesaccuracy: 95.8 -> 98.1Improved
use Euler embedding feature map instead of persistence image featuresPhi_PI · Shapesaccuracy: 90.3 -> 98.0Improved
use Betti kernel instead of sliced Wasserstein kernelk_SW · Texturesaccuracy: 96.8 -> 97.8Improved
use signature of persistence paths instead of persistence images on orbitsPhi_PI · Orbitsaccuracy: 99.86 -> 98.8Hurt
kernelize Betti embedding instead of direct feature map (ablation)Phi_beta · Texturesaccuracy: 96.6 -> 97.8Improved
kernelize envelope embedding instead of direct feature map (ablation)Phi_E · Texturesaccuracy: 88.1 -> 90.4Improved
use direct feature map instead of kernel for Euler embedding (ablation)k_chi · Shapesaccuracy: 92.4 -> 98.0Improved
use direct feature map instead of kernel for envelope embedding (ablation)k_E · Shapesaccuracy: 92.7 -> 95.0Improved
use direct feature map instead of kernel for envelope embedding (ablation)k_E · Orbitsaccuracy: 96.6 -> 98.1Improved
use landscape or naive path embedding instead of envelope, Betti, Euler (ablation)signature feature map · Textures, Orbits, ShapesaccuracyHurt
raise tensor truncation level M for feature maps (up to 8) vs kernels (2 or 3) (ablation)signature features · Textures, Orbits, Shapesbest MMixed

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