SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse

Documenti analoghi

• Memory-efficient Continual Learning with Neural Collapse Contrastive
  di: Dang, Trung-Anh, et al.
  Pubblicazione: (2024)
• IBMA: An Imputation-Based Mixup Augmentation Using Self-Supervised Learning for Time Series Data
  di: Nguyen, Dang Nha, et al.
  Pubblicazione: (2025)
• Explaining Graph Neural Networks via Structure-aware Interaction Index
  di: Bui, Ngoc, et al.
  Pubblicazione: (2024)
• Towards Explainable Clustering: A Constrained Declarative based Approach
  di: Guilbert, Mathieu, et al.
  Pubblicazione: (2024)
• Pushing Boundaries: Mixup's Influence on Neural Collapse
  di: Fisher, Quinn, et al.
  Pubblicazione: (2024)