AI Paper Atlas

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

Deep Transformation-Invariant Clustering

Tom Monnier, Thibault Groueix, Mathieu Aubry

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 1 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 transformation-invariant alignment with DTI K-means rather than pixel-space K-meansK-means · MNISTACC: 54.8 -> 97.3Improved
Add transformation-invariant alignment with DTI K-means rather than pixel-space K-meansK-means · Fashion-MNISTACC: 54.1 -> 61.2Improved
Use Gaussian-weighted clustering loss focused on the center digitDTI clustering on SVHN · SVHNACC: 36.4 / 44.5 -> 39.6 / 62.6Improved
Add morphological transformation (ablation)DTI clustering with affine and TPS · MNISTACC: 94.8 -> 97.3Improved
Add thin plate spline transformation (ablation)DTI clustering with affine and morphological transformation · MNISTACC: 90.0 -> 97.3Improved
Add affine transformation (ablation)DTI clustering with morphological and TPS transformations · MNISTACC: 85.1 -> 97.3Improved
Order modules affine, TPS, then morphological instead of affine, morphological, then TPS (ablation)DTI clustering · MNISTACC: 97.3 -> 95.5Hurt
Order modules morphological, affine, then TPS instead of affine, morphological, then TPS (ablation)DTI clustering · MNISTACC: 97.3 -> 27.5Hurt
Add empty cluster reassignment (ablation)DTI clustering · MNISTACC: 80.9 -> 97.3Improved
Add curriculum learning for transformation modules (ablation)DTI clustering · MNISTACC: 83.9 -> 97.3Improved
Use learned transformation predictors instead of directly optimizing per-sample transformations (ablation)Transformation-invariant clustering · MNISTACC: 26.3 -> 97.3Improved
Use learned transformation predictors instead of directly optimizing per-sample affine transformations (ablation)Transformation-invariant clustering · MNISTACC: 73.0 -> 97.3Improved

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