All-around Neural Collapse for Imbalanced Classification

no code implementations • 14 Aug 2024 • Enhao Zhang, Chaohua Li, Chuanxing Geng, Songcan Chen

Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach \textit{optimal} inter-class separability during the terminal phase of training on a \textit{balanced} dataset.

Classification imbalanced classification

All Beings Are Equal in Open Set Recognition

no code implementations • 31 Jan 2024 • Chaohua Li, Enhao Zhang, Chuanxing Geng, Songcan Chen

In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given $K$ known classes as an additional $K$+$1$-th class to explicitly model potential open space.

Contrastive Learning Open Set Learning