AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Differentiable Hierarchical Optimal Transport for Robust Multi-View Learning

Dixin Luo, Hongteng Xu, Lawrence Carin

TPAMI 2022 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 17 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
replace pairwise sliced Wasserstein with hierarchical OT (view clustering)multi-view learning · Caltech20 (unsupervised)classification accuracy (%): 60.85 -> 71.07 with K=3Improved
add autoencoder reconstruction regularizer R_S to HOT K=3 (ablation)HOT K=3 · Handwritten (semi-supervised)classification accuracy (%): 90.05 -> 91.07Improved
add autoencoder regularizer to HOT K=3 (ablation)HOT K=3 · Caltech7 (semi-supervised)classification accuracy (%): 88.29 -> 88.98Improved
use unaligned data with HOT K=3 AE instead of aligned AECCAHOT K=3 AE · Handwritten (semi-supervised)classification accuracy (%): 88.53 -> 91.07Improved
use HOT K=3 instead of AECCA in unsupervised modeHOT K=3 · Caltech20 (unsupervised)classification accuracy (%): 66.75 -> 71.07Improved
use K=3 view clusters in HOTHOT · Caltech7 (unsupervised)classification accuracy (%): 82.89 -> 86.27Improved
use K=3 view clusters in HOTHOT · Handwritten (unsupervised)classification accuracy (%): 67.65 -> 87.12Improved
add autoencoder regularizer to HOT (no K clusters) (ablation)HOT · Caltech20 (unsupervised)classification accuracy (%): 60.85 -> 67.41Improved
add autoencoder regularizer to HOT K=3 (ablation)HOT K=3 · Caltech20 (unsupervised)classification accuracy (%): 71.07 -> 69.48Hurt
remove HOG or LBP view (ablation)HOT model · Caltech7classification accuracy (%)Hurt
remove Gabor or CENTRIST view (ablation)HOT model · Caltech7classification accuracy (%)No clear effect

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