DoubleCCA merges CLIP text prompts with sentence-embedding-model features of random prompt variants via two CCA steps, improving worst-group accuracy of zero-shot classifiers without group labels or image data.
Hyperbolic image-text representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DoubleCCA: Improving Foundation Model Group Robustness with Random Sentence Embeddings
DoubleCCA merges CLIP text prompts with sentence-embedding-model features of random prompt variants via two CCA steps, improving worst-group accuracy of zero-shot classifiers without group labels or image data.