Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models

Documenti analoghi

• FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
  di: Goswami, Dipam, et al.
  Pubblicazione: (2023)
• Exemplar-free Continual Representation Learning via Learnable Drift Compensation
  di: Gomez-Villa, Alex, et al.
  Pubblicazione: (2024)
• Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
  di: Goswami, Dipam, et al.
  Pubblicazione: (2024)
• Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
  di: Goswami, Dipam, et al.
  Pubblicazione: (2024)
• IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
  di: Magistri, Simone, et al.
  Pubblicazione: (2026)