AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Supervised Dimensionality Reduction and Visualization using Centroid-Encoder

Tomojit Ghosh, Michael Kirby

NeurIPS 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning

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 pre-training to centroid-encoder (ablation)Centroid-encoder · MNISTk-NN (k=5) error %: 3.17 -> 2.61Improved
add pre-training to centroid-encoder (ablation)Centroid-encoder · USPSk-NN (k=5) error %: 2.98 -> 2.91No clear effect
use centroid-encoder instead of autoencoderautoencoder · MNISTk-NN (k=5) error %: 22.04 -> 2.61Improved
use centroid-encoder instead of supervised UMAPsupervised UMAP · MNISTk-NN (k=5) error %: 3.45 -> 2.61Improved
use centroid-encoder instead of nonlinear NCANNCA · USPSk-NN (k=5) error %: 6.58 -> 2.91Improved
use centroid-encoder instead of dt-MCML (with pre-training)dt-MCML · MNISTk-NN (k=5) error %: 2.03 -> 2.61Hurt
use centroid-encoder instead of dt-MCML (with pre-training)dt-MCML · USPSk-NN (k=5) error %: 2.46 -> 2.91Hurt
use centroid-encoder instead of dt-MCML (no pre-training)dt-MCML · USPSk-NN (k=5) error %: 4.07 -> 2.98Improved
use centroid-encoder instead of HOPE (no pre-training)HOPE · MNISTk-NN (k=5) error %: 3.20 -> 3.17No clear effect
use centroid-encoder instead of SUMAPSUMAP · Landsatk-NN (k=5) error %: 9.68 -> 8.97No clear effect
use centroid-encoder instead of SNeRV lambda=0.1SNeRV · Letterk-NN (k=5) error %: 22.96 -> 23.82Hurt
use centroid-encoder instead of S-IsomapS-Isomap · Phonemek-NN (k=5) error %: 8.61 -> 7.52Improved

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