AI Paper Atlas

Research map / Optimization / Optimizers

Siamese Networks: The Tale of Two Manifolds

Soumava Kumar Roy, Mehrtash Harandi, Richard Nock, Richard Hartley

ICCV 2019 · Optimization › Optimizers · approach: Second-order and structured preconditioning · 67 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 qConv layer instead of ordinary Conv embedding layer (ablation)Siamese network · MNIST1-NN error (%): 14.84 -> 9.93Improved
use Stiefel layer instead of ordinary Conv embedding layer (ablation)Siamese network · MNIST1-NN error (%): 14.84 -> 9.75Improved
use qConv layer instead of ordinary Conv embedding layer (ablation)shallow Siamese network · STL10NN accuracy (%): 42.7% -> 48.5%Improved
use Stiefel layer instead of ordinary Conv embedding layer (ablation)shallow Siamese network · STL10NN accuracy (%): 42.7% -> 48.6%Improved
add Riemannian geometry (Stiefel) to triplet-trained Inception (ablation)Trip-SH · CARS196Recall@1: 51.5 -> 73.2Improved
add Riemannian geometry (Stiefel) to triplet-trained Inception (ablation)Trip-SH · CUB-200-2011Recall@1: 42.6 -> 52.3Improved
add Riemannian geometry (Stiefel) to triplet-trained Inception (ablation)Trip-SH · SOPRecall@1: 66.7 -> 69.2Improved
Stiefel geometry versus recent complex methods DAML/DVML/DWS on CUBOurs (Stiefel) · CUB-200-2011Recall@1: 52.3 vs 52.7 (DVML)No clear effect
qConv training time overhead versus Conv per epoch (ablation)qConv · MNISTtime per epoch (sec): 12.1 -> 12.3No clear effect
qConv and Stiefel training time overhead versus Conv (ablation)Siamese network · STL10time per epoch (sec): 143 -> 150 and 152No 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