AI Paper Atlas

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

CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age

Dani Kiyasseh, Tingting Zhu, David A. Clifton

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 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
Use clinical prototypes as centroids rather than traditional prototypesCROCS clustering on Chapman · Chapman validationclass accuracy: 80.3 -> 90.3Improved
Use clinical prototypes rather than DTC prototypes for retrievalCROCS retrieval on Chapman · Chapman validation, K=1, at least 1 attribute matchprecision: 71.9 -> 95.6Improved
Use soft rather than hard assignment (ablation)CROCS clustering · PTB-XL validationclass accuracy: 66.5 -> 76.0Improved
Use modulated rather than uniform soft attraction (ablation)CROCS clustering · Chapman validationclass AMI: 68.2 -> 72.1Improved
Add the semantic-distance regularizer (ablation)CROCS clustering · Chapman validationclass AMI: 72.1 -> 72.8Improved
Set β to 0.2 rather than 0.05, 0.1, or 0.4 (ablation)CROCS clustering · PTB-XL validationclass accuracy: 66.0 -> 76.0; 65.7 -> 76.0; 65.9 -> 76.0Improved
Use CP CROCS rather than TP CROCS as the retrieval queryCROCS retrieval · PTB-XL validation, K=1, at least 1 attribute matchprecision: 99.0 -> 92.5Hurt
Reduce labelled training data to 10%CROCS clustering · Chapman validationclass accuracy: 90.3 -> 82.7Hurt
Vary embedding dimension across the tested sizes (ablation)CROCS clustering · Chapman class and sex assignmentaccuracyNo clear effect
Use β=0.2 instead of other tested β values (ablation)CROCS retrieval · PTB-XL validation, K=1, at least 1 attribute matchprecision: 63.5 -> 68.8; 63.5 -> 68.8; 67.5 -> 68.8Improved

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