CPT creates cluster-invariant spaces from pre-trained VLM semantics and applies neural collapse losses to boost long-tail performance and unseen-class generalization in prompt tuning.
Inductive state- relabeling adversarial active learning with heuristic clique rescaling.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 46(12):9780–9796
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
CPT creates cluster-invariant spaces from pre-trained VLM semantics and applies neural collapse losses to boost long-tail performance and unseen-class generalization in prompt tuning.