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
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
- Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame (NeurIPS 2024 · similarity 0.89)
- Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model (ICML 2024 · similarity 0.87)
- Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model (NeurIPS 2025 · similarity 0.87)
- Generalized Neural Collapse for a Large Number of Classes (ICML 2024 · similarity 0.87)
- Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data (NeurIPS 2025 · similarity 0.87)
- Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization (NeurIPS 2024 · similarity 0.86)
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.
