Analysis of the Island Class Structure in dimension-deficient deep classifiers
Abstract
Recent deep neural classifiers may operate under a dimension-deficient setting, where the feature dimension is insufficient relative to the number of classes and the symmetric geometry predicted by Neural Collapse cannot be realized. In this study, we focus on one resulting geometric structure, the Island Class Structure, which forms a bounded internal decision region near the origin. Using theoretical expressions of decision boundaries, we derive its emergence conditions and validate them experimentally on MNIST and CIFAR-10. The results show that this structure reproducibly appears as an intermediate geometric solution under severe low-dimensional constraints.
Fields of Study & Subjects
Face and Expression Recognition
Stochastic Gradient Optimization Techniques
Natural Language Processing Techniques
Publication details
- Journal / source
- Nonlinear Theory and Its Applications IEICE
- Publisher
- Institute of Electronics, Information and Communications Engineers (IEICE)
- Volume
- 17
- Issue
- 3
- Pages
- 1187–1212
- Publication date
- 1 January 2026
- Language
- EN