DiMPLe separates CLIP's image and text features into invariant and spurious components and claims large OOD accuracy gains through cross-modal alignment of the invariant parts.
Learning to prompt for open-vocabulary ob- ject detection with vision-language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation
DiMPLe separates CLIP's image and text features into invariant and spurious components and claims large OOD accuracy gains through cross-modal alignment of the invariant parts.