AI Paper Atlas

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

Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation

Hoyong Kim, Kangil Kim

ICLR 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

Read the paper

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a fixed non-negative orthogonal classifier that induces zero-mean neural collapse with feature dimension separation for classification.

Problem

Training dynamics of fixed orthogonal classifiers under neural collapse have not been studied, and fixed classifiers' interaction with feature geometry is unclear.

Approach

Uses a fixed non-negative orthogonal classifier to induce zero-mean neural collapse and separate feature dimensions, rather than learnable classifiers or prior fixed orthogonal ones.

Experimental setup

Baselines: learnable classifiers fixed orthogonal classifiers

Builds on: neural collapse fixed orthogonal classifier

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