conftrace_

Hoyong Kim

2 papers · 2022–2024 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze

Venues

ICLR (1) NeurIPS (1)

Top co-authors

Research topics

Deep Learning (2) Machine Learning (2) Techniques (2) Architectures (1) Core Methods (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

representation learning (1) continual learning (1) metric learning (1) few-shot learning (1) model architecture (1) inner product (1) angular similarity (1) neural collapse (1) feature normalization (1) spherization layer (1) hyperspherical representation (1) orthogonal classifier (1) hyperspherical surface (1) feature dimension separation (1)

Papers

Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation ICLR 2024 Spherization Layer: Representation Using Only Angles NeurIPS 2022