AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Building Deep Networks on Grassmann Manifolds

Zhiwu Huang, Jiqing Wu, Luc Van Gool

AAAI 2018 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence · 173 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
add a second Projection-Pooling block (ablation)GrNet · AFEW, HDM05, PaSC control, and PaSC handheldaccuracy / verification performance: 32.08% -> 34.23%; 57.73%$\pm$2.24 -> 59.23%$\pm$1.78; 80.15% -> 80.52%; 72.51% -> 72.76%Mixed
add Projection-Pooling blocks rather than use no blocks (ablation)GrNet · AFEW, HDM05, PaSC control, and PaSC handheldaccuracy / verification performance: 25.34% -> 34.23%; 51.12%$\pm$3.55 -> 59.23%$\pm$1.78; 68.52% -> 80.52%; 63.92% -> 72.76%Improved
remove ProjMap (Riemannian computing) (ablation)GrNet · AFEWaccuracy: 17.62%Hurt
remove ReOrth (geometry-aware learning) (ablation)GrNet · AFEWaccuracy: 26.15%Hurt
use multiple FRMap projections instead of a single projection (ablation)GrNet · three visual recognition datasetsperformanceImproved
use W-ProjPooling instead of A-ProjPooling (ablation)GrNet with M-FRMap · three visual recognition datasetsperformanceImproved
update FRMap weights on Stiefel manifolds instead of PSD manifolds (ablation)GrNet · four reported dataset evaluationsperformance: 32.13%, 57.25%, 80.15%, 71.28%Hurt
use GrNet rather than the strongest reported baselineGrNet-2Blocks · AFEW validationaccuracy: 34.23% -> 34.23%No clear effect
use GrNet rather than the strongest reported baselineGrNet-2Blocks · HDM05accuracy: 61.45%$\pm$1.12 -> 59.23%$\pm$1.78Hurt
use GrNet rather than the strongest reported baselineGrNet-2Blocks · PaSC controlverification performance: 80.12% -> 80.52%Improved
use GrNet rather than the strongest reported baselineGrNet-2Blocks · PaSC handheldverification performance: 72.83% -> 72.76%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