SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning

Documenti analoghi

• Online Zero-Shot Classification with CLIP
  di: Qian, Qi, et al.
  Pubblicazione: (2024)
• Understanding Adversarial Robustness from Feature Maps of Convolutional Layers
  di: Xu, Cong, et al.
  Pubblicazione: (2022)
• Variational Bayesian Last Layers
  di: Harrison, James, et al.
  Pubblicazione: (2024)
• Theoretical Guarantees of Data Augmented Last Layer Retraining Methods
  di: Welfert, Monica, et al.
  Pubblicazione: (2024)
• ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations
  di: Addepalli, Sravanti, et al.
  Pubblicazione: (2024)